Skip to content

Instantly share code, notes, and snippets.

@kshirsagarsiddharth

kshirsagarsiddharth/fillna.ipynb

Created December 25, 2019 19:32
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save kshirsagarsiddharth/e002e6e0f9ea6b2e5537015e07d029dd to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save kshirsagarsiddharth/e002e6e0f9ea6b2e5537015e07d029dd to your computer and use it in GitHub Desktop.
Download ZIP
Created on Cognitive Class Labs
Display the source blob
Display the rendered blob
Raw
fillna.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Functions for removing null values\n",
"1) isnull()\n",
"2) notnull()\n",
"3) dropna()\n",
"4) fillna()\n",
"5) replace()\n",
"6) interpolate()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"dict = {'First Score':[100, 90, np.nan, 95], \n",
" 'Second Score': [30, 45, 56, np.nan], \n",
" 'Third Score':[np.nan, 40, 80, 98]} \n",
"df = pd.DataFrame(dict)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 False False True\n",
"1 False False False\n",
"2 True False False\n",
"3 False True False"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.isnull()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"data = pd.read_csv('employees2.csv')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Name</th>\n",
" <th>Gender</th>\n",
" <th>Start Date</th>\n",
" <th>Last Login Time</th>\n",
" <th>Salary</th>\n",
" <th>Bonus %</th>\n",
" <th>Senior Management</th>\n",
" <th>Team</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Douglas</td>\n",
" <td>Male</td>\n",
" <td>8/6/1993</td>\n",
" <td>12:42 PM</td>\n",
" <td>97308</td>\n",
" <td>6.945</td>\n",
" <td>True</td>\n",
" <td>Marketing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Thomas</td>\n",
" <td>Male</td>\n",
" <td>3/31/1996</td>\n",
" <td>6:53 AM</td>\n",
" <td>61933</td>\n",
" <td>4.170</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Maria</td>\n",
" <td>Female</td>\n",
" <td>4/23/1993</td>\n",
" <td>11:17 AM</td>\n",
" <td>130590</td>\n",
" <td>11.858</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Jerry</td>\n",
" <td>Male</td>\n",
" <td>3/4/2005</td>\n",
" <td>1:00 PM</td>\n",
" <td>138705</td>\n",
" <td>9.340</td>\n",
" <td>True</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>1/24/1998</td>\n",
" <td>4:47 PM</td>\n",
" <td>101004</td>\n",
" <td>1.389</td>\n",
" <td>True</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>995</th>\n",
" <td>Henry</td>\n",
" <td>NaN</td>\n",
" <td>11/23/2014</td>\n",
" <td>6:09 AM</td>\n",
" <td>132483</td>\n",
" <td>16.655</td>\n",
" <td>False</td>\n",
" <td>Distribution</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>Phillip</td>\n",
" <td>Male</td>\n",
" <td>1/31/1984</td>\n",
" <td>6:30 AM</td>\n",
" <td>42392</td>\n",
" <td>19.675</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>Russell</td>\n",
" <td>Male</td>\n",
" <td>5/20/2013</td>\n",
" <td>12:39 PM</td>\n",
" <td>96914</td>\n",
" <td>1.421</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>4/20/2013</td>\n",
" <td>4:45 PM</td>\n",
" <td>60500</td>\n",
" <td>11.985</td>\n",
" <td>False</td>\n",
" <td>Business Development</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>Albert</td>\n",
" <td>Male</td>\n",
" <td>5/15/2012</td>\n",
" <td>6:24 PM</td>\n",
" <td>129949</td>\n",
" <td>10.169</td>\n",
" <td>True</td>\n",
" <td>Sales</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1000 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" First Name Gender Start Date Last Login Time Salary Bonus % \\\n",
"0 Douglas Male 8/6/1993 12:42 PM 97308 6.945 \n",
"1 Thomas Male 3/31/1996 6:53 AM 61933 4.170 \n",
"2 Maria Female 4/23/1993 11:17 AM 130590 11.858 \n",
"3 Jerry Male 3/4/2005 1:00 PM 138705 9.340 \n",
"4 Larry Male 1/24/1998 4:47 PM 101004 1.389 \n",
".. ... ... ... ... ... ... \n",
"995 Henry NaN 11/23/2014 6:09 AM 132483 16.655 \n",
"996 Phillip Male 1/31/1984 6:30 AM 42392 19.675 \n",
"997 Russell Male 5/20/2013 12:39 PM 96914 1.421 \n",
"998 Larry Male 4/20/2013 4:45 PM 60500 11.985 \n",
"999 Albert Male 5/15/2012 6:24 PM 129949 10.169 \n",
"\n",
" Senior Management Team \n",
"0 True Marketing \n",
"1 True NaN \n",
"2 False Finance \n",
"3 True Finance \n",
"4 True Client Services \n",
".. ... ... \n",
"995 False Distribution \n",
"996 False Finance \n",
"997 False Product \n",
"998 False Business Development \n",
"999 True Sales \n",
"\n",
"[1000 rows x 8 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"bool_series = pd.isnull(data['Gender'])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 False\n",
"1 False\n",
"2 False\n",
"3 False\n",
"4 False\n",
" ... \n",
"995 True\n",
"996 False\n",
"997 False\n",
"998 False\n",
"999 False\n",
"Name: Gender, Length: 1000, dtype: bool"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bool_series #data with value where gender is not mentioned"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Name</th>\n",
" <th>Gender</th>\n",
" <th>Start Date</th>\n",
" <th>Last Login Time</th>\n",
" <th>Salary</th>\n",
" <th>Bonus %</th>\n",
" <th>Senior Management</th>\n",
" <th>Team</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Lois</td>\n",
" <td>NaN</td>\n",
" <td>4/22/1995</td>\n",
" <td>7:18 PM</td>\n",
" <td>64714</td>\n",
" <td>4.934</td>\n",
" <td>True</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>Joshua</td>\n",
" <td>NaN</td>\n",
" <td>3/8/2012</td>\n",
" <td>1:58 AM</td>\n",
" <td>90816</td>\n",
" <td>18.816</td>\n",
" <td>True</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>Scott</td>\n",
" <td>NaN</td>\n",
" <td>7/11/1991</td>\n",
" <td>6:58 PM</td>\n",
" <td>122367</td>\n",
" <td>5.218</td>\n",
" <td>False</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>Joyce</td>\n",
" <td>NaN</td>\n",
" <td>2/20/2005</td>\n",
" <td>2:40 PM</td>\n",
" <td>88657</td>\n",
" <td>12.752</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>Christine</td>\n",
" <td>NaN</td>\n",
" <td>6/28/2015</td>\n",
" <td>1:08 AM</td>\n",
" <td>66582</td>\n",
" <td>11.308</td>\n",
" <td>True</td>\n",
" <td>Business Development</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>961</th>\n",
" <td>Antonio</td>\n",
" <td>NaN</td>\n",
" <td>6/18/1989</td>\n",
" <td>9:37 PM</td>\n",
" <td>103050</td>\n",
" <td>3.050</td>\n",
" <td>False</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>972</th>\n",
" <td>Victor</td>\n",
" <td>NaN</td>\n",
" <td>7/28/2006</td>\n",
" <td>2:49 PM</td>\n",
" <td>76381</td>\n",
" <td>11.159</td>\n",
" <td>True</td>\n",
" <td>Sales</td>\n",
" </tr>\n",
" <tr>\n",
" <th>985</th>\n",
" <td>Stephen</td>\n",
" <td>NaN</td>\n",
" <td>7/10/1983</td>\n",
" <td>8:10 PM</td>\n",
" <td>85668</td>\n",
" <td>1.909</td>\n",
" <td>False</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>989</th>\n",
" <td>Justin</td>\n",
" <td>NaN</td>\n",
" <td>2/10/1991</td>\n",
" <td>4:58 PM</td>\n",
" <td>38344</td>\n",
" <td>3.794</td>\n",
" <td>False</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>995</th>\n",
" <td>Henry</td>\n",
" <td>NaN</td>\n",
" <td>11/23/2014</td>\n",
" <td>6:09 AM</td>\n",
" <td>132483</td>\n",
" <td>16.655</td>\n",
" <td>False</td>\n",
" <td>Distribution</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>145 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" First Name Gender Start Date Last Login Time Salary Bonus % \\\n",
"20 Lois NaN 4/22/1995 7:18 PM 64714 4.934 \n",
"22 Joshua NaN 3/8/2012 1:58 AM 90816 18.816 \n",
"27 Scott NaN 7/11/1991 6:58 PM 122367 5.218 \n",
"31 Joyce NaN 2/20/2005 2:40 PM 88657 12.752 \n",
"41 Christine NaN 6/28/2015 1:08 AM 66582 11.308 \n",
".. ... ... ... ... ... ... \n",
"961 Antonio NaN 6/18/1989 9:37 PM 103050 3.050 \n",
"972 Victor NaN 7/28/2006 2:49 PM 76381 11.159 \n",
"985 Stephen NaN 7/10/1983 8:10 PM 85668 1.909 \n",
"989 Justin NaN 2/10/1991 4:58 PM 38344 3.794 \n",
"995 Henry NaN 11/23/2014 6:09 AM 132483 16.655 \n",
"\n",
" Senior Management Team \n",
"20 True Legal \n",
"22 True Client Services \n",
"27 False Legal \n",
"31 False Product \n",
"41 True Business Development \n",
".. ... ... \n",
"961 False Legal \n",
"972 True Sales \n",
"985 False Legal \n",
"989 False Legal \n",
"995 False Distribution \n",
"\n",
"[145 rows x 8 columns]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data[bool_series] #filtering data displaying data where Gender is not mentioned"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"dict = {'First Score':[100, 90, np.nan, 95], \n",
" 'Second Score': [30, 45, 56, np.nan], \n",
" 'Third Score':[np.nan, 40, 80, 98]} \n",
"df = pd.DataFrame(dict) "
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>45.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>56.0</td>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>NaN</td>\n",
" <td>98.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 100.0 30.0 NaN\n",
"1 90.0 45.0 40.0\n",
"2 NaN 56.0 80.0\n",
"3 95.0 NaN 98.0"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 False False True\n",
"1 False False False\n",
"2 True False False\n",
"3 False True False"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.isnull()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 True True False\n",
"1 True True True\n",
"2 False True True\n",
"3 True False True"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.notnull()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"bool_series = pd.notnull(data['Gender'])"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Name</th>\n",
" <th>Gender</th>\n",
" <th>Start Date</th>\n",
" <th>Last Login Time</th>\n",
" <th>Salary</th>\n",
" <th>Bonus %</th>\n",
" <th>Senior Management</th>\n",
" <th>Team</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Douglas</td>\n",
" <td>Male</td>\n",
" <td>8/6/1993</td>\n",
" <td>12:42 PM</td>\n",
" <td>97308</td>\n",
" <td>6.945</td>\n",
" <td>True</td>\n",
" <td>Marketing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Thomas</td>\n",
" <td>Male</td>\n",
" <td>3/31/1996</td>\n",
" <td>6:53 AM</td>\n",
" <td>61933</td>\n",
" <td>4.170</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Maria</td>\n",
" <td>Female</td>\n",
" <td>4/23/1993</td>\n",
" <td>11:17 AM</td>\n",
" <td>130590</td>\n",
" <td>11.858</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Jerry</td>\n",
" <td>Male</td>\n",
" <td>3/4/2005</td>\n",
" <td>1:00 PM</td>\n",
" <td>138705</td>\n",
" <td>9.340</td>\n",
" <td>True</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>1/24/1998</td>\n",
" <td>4:47 PM</td>\n",
" <td>101004</td>\n",
" <td>1.389</td>\n",
" <td>True</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>994</th>\n",
" <td>George</td>\n",
" <td>Male</td>\n",
" <td>6/21/2013</td>\n",
" <td>5:47 PM</td>\n",
" <td>98874</td>\n",
" <td>4.479</td>\n",
" <td>True</td>\n",
" <td>Marketing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>Phillip</td>\n",
" <td>Male</td>\n",
" <td>1/31/1984</td>\n",
" <td>6:30 AM</td>\n",
" <td>42392</td>\n",
" <td>19.675</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>Russell</td>\n",
" <td>Male</td>\n",
" <td>5/20/2013</td>\n",
" <td>12:39 PM</td>\n",
" <td>96914</td>\n",
" <td>1.421</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>4/20/2013</td>\n",
" <td>4:45 PM</td>\n",
" <td>60500</td>\n",
" <td>11.985</td>\n",
" <td>False</td>\n",
" <td>Business Development</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>Albert</td>\n",
" <td>Male</td>\n",
" <td>5/15/2012</td>\n",
" <td>6:24 PM</td>\n",
" <td>129949</td>\n",
" <td>10.169</td>\n",
" <td>True</td>\n",
" <td>Sales</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>855 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" First Name Gender Start Date Last Login Time Salary Bonus % \\\n",
"0 Douglas Male 8/6/1993 12:42 PM 97308 6.945 \n",
"1 Thomas Male 3/31/1996 6:53 AM 61933 4.170 \n",
"2 Maria Female 4/23/1993 11:17 AM 130590 11.858 \n",
"3 Jerry Male 3/4/2005 1:00 PM 138705 9.340 \n",
"4 Larry Male 1/24/1998 4:47 PM 101004 1.389 \n",
".. ... ... ... ... ... ... \n",
"994 George Male 6/21/2013 5:47 PM 98874 4.479 \n",
"996 Phillip Male 1/31/1984 6:30 AM 42392 19.675 \n",
"997 Russell Male 5/20/2013 12:39 PM 96914 1.421 \n",
"998 Larry Male 4/20/2013 4:45 PM 60500 11.985 \n",
"999 Albert Male 5/15/2012 6:24 PM 129949 10.169 \n",
"\n",
" Senior Management Team \n",
"0 True Marketing \n",
"1 True NaN \n",
"2 False Finance \n",
"3 True Finance \n",
"4 True Client Services \n",
".. ... ... \n",
"994 True Marketing \n",
"996 False Finance \n",
"997 False Product \n",
"998 False Business Development \n",
"999 True Sales \n",
"\n",
"[855 rows x 8 columns]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data[bool_series] #printing all the data where gender is not null"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"dict = {'First Score':[100, 90, np.nan, 95], \n",
" 'Second Score': [30, 45, 56, np.nan], \n",
" 'Third Score':[np.nan, 40, 80, 98]} \n",
" \n",
"# creating a dataframe from dictionary \n",
"df = pd.DataFrame(dict) "
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>45.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.0</td>\n",
" <td>56.0</td>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>0.0</td>\n",
" <td>98.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 100.0 30.0 0.0\n",
"1 90.0 45.0 40.0\n",
"2 0.0 56.0 80.0\n",
"3 95.0 0.0 98.0"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.fillna(0)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"dict = {'First Score':[100, 90, np.nan, 95], \n",
" 'Second Score': [30, 45, 56, np.nan], \n",
" 'Third Score':[np.nan, 40, 80, 98]} \n",
" \n",
"# creating a dataframe from dictionary \n",
"df = pd.DataFrame(dict) "
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>45.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>90.0</td>\n",
" <td>56.0</td>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>56.0</td>\n",
" <td>98.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 100.0 30.0 NaN\n",
"1 90.0 45.0 40.0\n",
"2 90.0 56.0 80.0\n",
"3 95.0 56.0 98.0"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.fillna(method = 'pad')\n",
"#filling the missing value with previous onse"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>45.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>95.0</td>\n",
" <td>56.0</td>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>NaN</td>\n",
" <td>98.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 100.0 30.0 40.0\n",
"1 90.0 45.0 40.0\n",
"2 95.0 56.0 80.0\n",
"3 95.0 NaN 98.0"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.fillna(method='bfill') #filling null values with next onse"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Name</th>\n",
" <th>Gender</th>\n",
" <th>Start Date</th>\n",
" <th>Last Login Time</th>\n",
" <th>Salary</th>\n",
" <th>Bonus %</th>\n",
" <th>Senior Management</th>\n",
" <th>Team</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>Louise</td>\n",
" <td>Female</td>\n",
" <td>8/12/1980</td>\n",
" <td>9:01 AM</td>\n",
" <td>63241</td>\n",
" <td>15.132</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Julie</td>\n",
" <td>Female</td>\n",
" <td>10/26/1997</td>\n",
" <td>3:19 PM</td>\n",
" <td>102508</td>\n",
" <td>12.637</td>\n",
" <td>True</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>Brandon</td>\n",
" <td>Male</td>\n",
" <td>12/1/1980</td>\n",
" <td>1:08 AM</td>\n",
" <td>112807</td>\n",
" <td>17.492</td>\n",
" <td>True</td>\n",
" <td>Human Resources</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>Gary</td>\n",
" <td>Male</td>\n",
" <td>1/27/2008</td>\n",
" <td>11:40 PM</td>\n",
" <td>109831</td>\n",
" <td>5.831</td>\n",
" <td>False</td>\n",
" <td>Sales</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>Kimberly</td>\n",
" <td>Female</td>\n",
" <td>1/14/1999</td>\n",
" <td>7:13 AM</td>\n",
" <td>41426</td>\n",
" <td>14.543</td>\n",
" <td>True</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Lillian</td>\n",
" <td>Female</td>\n",
" <td>6/5/2016</td>\n",
" <td>6:09 AM</td>\n",
" <td>59414</td>\n",
" <td>1.256</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>Jeremy</td>\n",
" <td>Male</td>\n",
" <td>9/21/2010</td>\n",
" <td>5:56 AM</td>\n",
" <td>90370</td>\n",
" <td>7.369</td>\n",
" <td>False</td>\n",
" <td>Human Resources</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>Shawn</td>\n",
" <td>Male</td>\n",
" <td>12/7/1986</td>\n",
" <td>7:45 PM</td>\n",
" <td>111737</td>\n",
" <td>6.414</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>Diana</td>\n",
" <td>Female</td>\n",
" <td>10/23/1981</td>\n",
" <td>10:27 AM</td>\n",
" <td>132940</td>\n",
" <td>19.082</td>\n",
" <td>False</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>Donna</td>\n",
" <td>Female</td>\n",
" <td>7/22/2010</td>\n",
" <td>3:48 AM</td>\n",
" <td>81014</td>\n",
" <td>1.894</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Lois</td>\n",
" <td>NaN</td>\n",
" <td>4/22/1995</td>\n",
" <td>7:18 PM</td>\n",
" <td>64714</td>\n",
" <td>4.934</td>\n",
" <td>True</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>Matthew</td>\n",
" <td>Male</td>\n",
" <td>9/5/1995</td>\n",
" <td>2:12 AM</td>\n",
" <td>100612</td>\n",
" <td>13.645</td>\n",
" <td>False</td>\n",
" <td>Marketing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>Joshua</td>\n",
" <td>NaN</td>\n",
" <td>3/8/2012</td>\n",
" <td>1:58 AM</td>\n",
" <td>90816</td>\n",
" <td>18.816</td>\n",
" <td>True</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>NaN</td>\n",
" <td>Male</td>\n",
" <td>6/14/2012</td>\n",
" <td>4:19 PM</td>\n",
" <td>125792</td>\n",
" <td>5.042</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>John</td>\n",
" <td>Male</td>\n",
" <td>7/1/1992</td>\n",
" <td>10:08 PM</td>\n",
" <td>97950</td>\n",
" <td>13.873</td>\n",
" <td>False</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Name Gender Start Date Last Login Time Salary Bonus % \\\n",
"10 Louise Female 8/12/1980 9:01 AM 63241 15.132 \n",
"11 Julie Female 10/26/1997 3:19 PM 102508 12.637 \n",
"12 Brandon Male 12/1/1980 1:08 AM 112807 17.492 \n",
"13 Gary Male 1/27/2008 11:40 PM 109831 5.831 \n",
"14 Kimberly Female 1/14/1999 7:13 AM 41426 14.543 \n",
"15 Lillian Female 6/5/2016 6:09 AM 59414 1.256 \n",
"16 Jeremy Male 9/21/2010 5:56 AM 90370 7.369 \n",
"17 Shawn Male 12/7/1986 7:45 PM 111737 6.414 \n",
"18 Diana Female 10/23/1981 10:27 AM 132940 19.082 \n",
"19 Donna Female 7/22/2010 3:48 AM 81014 1.894 \n",
"20 Lois NaN 4/22/1995 7:18 PM 64714 4.934 \n",
"21 Matthew Male 9/5/1995 2:12 AM 100612 13.645 \n",
"22 Joshua NaN 3/8/2012 1:58 AM 90816 18.816 \n",
"23 NaN Male 6/14/2012 4:19 PM 125792 5.042 \n",
"24 John Male 7/1/1992 10:08 PM 97950 13.873 \n",
"\n",
" Senior Management Team \n",
"10 True NaN \n",
"11 True Legal \n",
"12 True Human Resources \n",
"13 False Sales \n",
"14 True Finance \n",
"15 False Product \n",
"16 False Human Resources \n",
"17 False Product \n",
"18 False Client Services \n",
"19 False Product \n",
"20 True Legal \n",
"21 False Marketing \n",
"22 True Client Services \n",
"23 NaN NaN \n",
"24 False Client Services "
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data[10:25]"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"data['Gender'].fillna('No Gender',inplace = True)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Name</th>\n",
" <th>Gender</th>\n",
" <th>Start Date</th>\n",
" <th>Last Login Time</th>\n",
" <th>Salary</th>\n",
" <th>Bonus %</th>\n",
" <th>Senior Management</th>\n",
" <th>Team</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Douglas</td>\n",
" <td>Male</td>\n",
" <td>8/6/1993</td>\n",
" <td>12:42 PM</td>\n",
" <td>97308</td>\n",
" <td>6.945</td>\n",
" <td>True</td>\n",
" <td>Marketing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Thomas</td>\n",
" <td>Male</td>\n",
" <td>3/31/1996</td>\n",
" <td>6:53 AM</td>\n",
" <td>61933</td>\n",
" <td>4.170</td>\n",
" <td>True</td>\n",
" <td>-99</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Maria</td>\n",
" <td>Female</td>\n",
" <td>4/23/1993</td>\n",
" <td>11:17 AM</td>\n",
" <td>130590</td>\n",
" <td>11.858</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Jerry</td>\n",
" <td>Male</td>\n",
" <td>3/4/2005</td>\n",
" <td>1:00 PM</td>\n",
" <td>138705</td>\n",
" <td>9.340</td>\n",
" <td>True</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>1/24/1998</td>\n",
" <td>4:47 PM</td>\n",
" <td>101004</td>\n",
" <td>1.389</td>\n",
" <td>True</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>995</th>\n",
" <td>Henry</td>\n",
" <td>No Gender</td>\n",
" <td>11/23/2014</td>\n",
" <td>6:09 AM</td>\n",
" <td>132483</td>\n",
" <td>16.655</td>\n",
" <td>False</td>\n",
" <td>Distribution</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>Phillip</td>\n",
" <td>Male</td>\n",
" <td>1/31/1984</td>\n",
" <td>6:30 AM</td>\n",
" <td>42392</td>\n",
" <td>19.675</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>Russell</td>\n",
" <td>Male</td>\n",
" <td>5/20/2013</td>\n",
" <td>12:39 PM</td>\n",
" <td>96914</td>\n",
" <td>1.421</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>4/20/2013</td>\n",
" <td>4:45 PM</td>\n",
" <td>60500</td>\n",
" <td>11.985</td>\n",
" <td>False</td>\n",
" <td>Business Development</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>Albert</td>\n",
" <td>Male</td>\n",
" <td>5/15/2012</td>\n",
" <td>6:24 PM</td>\n",
" <td>129949</td>\n",
" <td>10.169</td>\n",
" <td>True</td>\n",
" <td>Sales</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1000 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" First Name Gender Start Date Last Login Time Salary Bonus % \\\n",
"0 Douglas Male 8/6/1993 12:42 PM 97308 6.945 \n",
"1 Thomas Male 3/31/1996 6:53 AM 61933 4.170 \n",
"2 Maria Female 4/23/1993 11:17 AM 130590 11.858 \n",
"3 Jerry Male 3/4/2005 1:00 PM 138705 9.340 \n",
"4 Larry Male 1/24/1998 4:47 PM 101004 1.389 \n",
".. ... ... ... ... ... ... \n",
"995 Henry No Gender 11/23/2014 6:09 AM 132483 16.655 \n",
"996 Phillip Male 1/31/1984 6:30 AM 42392 19.675 \n",
"997 Russell Male 5/20/2013 12:39 PM 96914 1.421 \n",
"998 Larry Male 4/20/2013 4:45 PM 60500 11.985 \n",
"999 Albert Male 5/15/2012 6:24 PM 129949 10.169 \n",
"\n",
" Senior Management Team \n",
"0 True Marketing \n",
"1 True -99 \n",
"2 False Finance \n",
"3 True Finance \n",
"4 True Client Services \n",
".. ... ... \n",
"995 False Distribution \n",
"996 False Finance \n",
"997 False Product \n",
"998 False Business Development \n",
"999 True Sales \n",
"\n",
"[1000 rows x 8 columns]"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.replace(to_replace = np.nan,value = -99)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>45.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>56.0</td>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>NaN</td>\n",
" <td>98.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 100.0 30.0 NaN\n",
"1 90.0 45.0 40.0\n",
"2 NaN 56.0 80.0\n",
"3 95.0 NaN 98.0"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>45.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"1 90.0 45.0 40.0"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dropna()"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>45.0</td>\n",
" <td>40.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>56.0</td>\n",
" <td>80.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>NaN</td>\n",
" <td>98.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score\n",
"0 100.0 30.0 NaN\n",
"1 90.0 45.0 40.0\n",
"2 NaN 56.0 80.0\n",
"3 95.0 NaN 98.0"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dropna(how='all')"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
"dict = {'First Score':[100, 90, np.nan, 95], \n",
" 'Second Score': [30, np.nan, 45, 56], \n",
" 'Third Score':[52, 40, 80, 98], \n",
" 'Fourth Score':[np.nan, np.nan, np.nan, 65]} \n",
" \n",
"# creating a dataframe from dictionary \n",
"df = pd.DataFrame(dict) "
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" <th>Fourth Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>52</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>NaN</td>\n",
" <td>40</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>45.0</td>\n",
" <td>80</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>56.0</td>\n",
" <td>98</td>\n",
" <td>65.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score Fourth Score\n",
"0 100.0 30.0 52 NaN\n",
"1 90.0 NaN 40 NaN\n",
"2 NaN 45.0 80 NaN\n",
"3 95.0 56.0 98 65.0"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" <th>Fourth Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>52</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>90.0</td>\n",
" <td>NaN</td>\n",
" <td>40</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>45.0</td>\n",
" <td>80</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>56.0</td>\n",
" <td>98</td>\n",
" <td>65.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score Fourth Score\n",
"0 100.0 30.0 52 NaN\n",
"1 90.0 NaN 40 NaN\n",
"2 NaN 45.0 80 NaN\n",
"3 95.0 56.0 98 65.0"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dropna(how='all')"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" <th>Fourth Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>52.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>45.0</td>\n",
" <td>80.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>56.0</td>\n",
" <td>98.0</td>\n",
" <td>65.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score Fourth Score\n",
"0 100.0 30.0 52.0 NaN\n",
"2 NaN 45.0 80.0 NaN\n",
"3 95.0 56.0 98.0 65.0"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# importing pandas as pd \n",
"import pandas as pd \n",
"\n",
"# importing numpy as np \n",
"import numpy as np \n",
"\n",
"# dictionary of lists \n",
"dict = {'First Score':[100, np.nan, np.nan, 95], \n",
"\t\t'Second Score': [30, np.nan, 45, 56], \n",
"\t\t'Third Score':[52, np.nan, 80, 98], \n",
"\t\t'Fourth Score':[np.nan, np.nan, np.nan, 65]} \n",
"\n",
"df = pd.DataFrame(dict) \n",
"\n",
"# using dropna() function\t \n",
"df.dropna(how = 'all') \n"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [],
"source": [
"dict = {'First Score':[100, np.nan, np.nan, 95], \n",
" 'Second Score': [30, np.nan, 45, 56], \n",
" 'Third Score':[52, np.nan, 80, 98], \n",
" 'Fourth Score':[60, 67, 68, 65]} \n",
" \n",
"# creating a dataframe from dictionary \n",
"df = pd.DataFrame(dict) \n",
" "
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Score</th>\n",
" <th>Second Score</th>\n",
" <th>Third Score</th>\n",
" <th>Fourth Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100.0</td>\n",
" <td>30.0</td>\n",
" <td>52.0</td>\n",
" <td>60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>67</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>45.0</td>\n",
" <td>80.0</td>\n",
" <td>68</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>95.0</td>\n",
" <td>56.0</td>\n",
" <td>98.0</td>\n",
" <td>65</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" First Score Second Score Third Score Fourth Score\n",
"0 100.0 30.0 52.0 60\n",
"1 NaN NaN NaN 67\n",
"2 NaN 45.0 80.0 68\n",
"3 95.0 56.0 98.0 65"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Fourth Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>67</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>68</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>65</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Fourth Score\n",
"0 60\n",
"1 67\n",
"2 68\n",
"3 65"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dropna(axis=1) #drop along all the columns"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Name</th>\n",
" <th>Gender</th>\n",
" <th>Start Date</th>\n",
" <th>Last Login Time</th>\n",
" <th>Salary</th>\n",
" <th>Bonus %</th>\n",
" <th>Senior Management</th>\n",
" <th>Team</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Douglas</td>\n",
" <td>Male</td>\n",
" <td>8/6/1993</td>\n",
" <td>12:42 PM</td>\n",
" <td>97308</td>\n",
" <td>6.945</td>\n",
" <td>True</td>\n",
" <td>Marketing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Thomas</td>\n",
" <td>Male</td>\n",
" <td>3/31/1996</td>\n",
" <td>6:53 AM</td>\n",
" <td>61933</td>\n",
" <td>4.170</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Maria</td>\n",
" <td>Female</td>\n",
" <td>4/23/1993</td>\n",
" <td>11:17 AM</td>\n",
" <td>130590</td>\n",
" <td>11.858</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Jerry</td>\n",
" <td>Male</td>\n",
" <td>3/4/2005</td>\n",
" <td>1:00 PM</td>\n",
" <td>138705</td>\n",
" <td>9.340</td>\n",
" <td>True</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>1/24/1998</td>\n",
" <td>4:47 PM</td>\n",
" <td>101004</td>\n",
" <td>1.389</td>\n",
" <td>True</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>995</th>\n",
" <td>Henry</td>\n",
" <td>No Gender</td>\n",
" <td>11/23/2014</td>\n",
" <td>6:09 AM</td>\n",
" <td>132483</td>\n",
" <td>16.655</td>\n",
" <td>False</td>\n",
" <td>Distribution</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>Phillip</td>\n",
" <td>Male</td>\n",
" <td>1/31/1984</td>\n",
" <td>6:30 AM</td>\n",
" <td>42392</td>\n",
" <td>19.675</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>Russell</td>\n",
" <td>Male</td>\n",
" <td>5/20/2013</td>\n",
" <td>12:39 PM</td>\n",
" <td>96914</td>\n",
" <td>1.421</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>4/20/2013</td>\n",
" <td>4:45 PM</td>\n",
" <td>60500</td>\n",
" <td>11.985</td>\n",
" <td>False</td>\n",
" <td>Business Development</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>Albert</td>\n",
" <td>Male</td>\n",
" <td>5/15/2012</td>\n",
" <td>6:24 PM</td>\n",
" <td>129949</td>\n",
" <td>10.169</td>\n",
" <td>True</td>\n",
" <td>Sales</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1000 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" First Name Gender Start Date Last Login Time Salary Bonus % \\\n",
"0 Douglas Male 8/6/1993 12:42 PM 97308 6.945 \n",
"1 Thomas Male 3/31/1996 6:53 AM 61933 4.170 \n",
"2 Maria Female 4/23/1993 11:17 AM 130590 11.858 \n",
"3 Jerry Male 3/4/2005 1:00 PM 138705 9.340 \n",
"4 Larry Male 1/24/1998 4:47 PM 101004 1.389 \n",
".. ... ... ... ... ... ... \n",
"995 Henry No Gender 11/23/2014 6:09 AM 132483 16.655 \n",
"996 Phillip Male 1/31/1984 6:30 AM 42392 19.675 \n",
"997 Russell Male 5/20/2013 12:39 PM 96914 1.421 \n",
"998 Larry Male 4/20/2013 4:45 PM 60500 11.985 \n",
"999 Albert Male 5/15/2012 6:24 PM 129949 10.169 \n",
"\n",
" Senior Management Team \n",
"0 True Marketing \n",
"1 True NaN \n",
"2 False Finance \n",
"3 True Finance \n",
"4 True Client Services \n",
".. ... ... \n",
"995 False Distribution \n",
"996 False Finance \n",
"997 False Product \n",
"998 False Business Development \n",
"999 True Sales \n",
"\n",
"[1000 rows x 8 columns]"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [],
"source": [
"new_data = data.dropna(axis = 0,how='any') # if in any row if there is a null value we drop thet particular row"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>First Name</th>\n",
" <th>Gender</th>\n",
" <th>Start Date</th>\n",
" <th>Last Login Time</th>\n",
" <th>Salary</th>\n",
" <th>Bonus %</th>\n",
" <th>Senior Management</th>\n",
" <th>Team</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Douglas</td>\n",
" <td>Male</td>\n",
" <td>8/6/1993</td>\n",
" <td>12:42 PM</td>\n",
" <td>97308</td>\n",
" <td>6.945</td>\n",
" <td>True</td>\n",
" <td>Marketing</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Maria</td>\n",
" <td>Female</td>\n",
" <td>4/23/1993</td>\n",
" <td>11:17 AM</td>\n",
" <td>130590</td>\n",
" <td>11.858</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Jerry</td>\n",
" <td>Male</td>\n",
" <td>3/4/2005</td>\n",
" <td>1:00 PM</td>\n",
" <td>138705</td>\n",
" <td>9.340</td>\n",
" <td>True</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>1/24/1998</td>\n",
" <td>4:47 PM</td>\n",
" <td>101004</td>\n",
" <td>1.389</td>\n",
" <td>True</td>\n",
" <td>Client Services</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Dennis</td>\n",
" <td>Male</td>\n",
" <td>4/18/1987</td>\n",
" <td>1:35 AM</td>\n",
" <td>115163</td>\n",
" <td>10.125</td>\n",
" <td>False</td>\n",
" <td>Legal</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>995</th>\n",
" <td>Henry</td>\n",
" <td>No Gender</td>\n",
" <td>11/23/2014</td>\n",
" <td>6:09 AM</td>\n",
" <td>132483</td>\n",
" <td>16.655</td>\n",
" <td>False</td>\n",
" <td>Distribution</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>Phillip</td>\n",
" <td>Male</td>\n",
" <td>1/31/1984</td>\n",
" <td>6:30 AM</td>\n",
" <td>42392</td>\n",
" <td>19.675</td>\n",
" <td>False</td>\n",
" <td>Finance</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>Russell</td>\n",
" <td>Male</td>\n",
" <td>5/20/2013</td>\n",
" <td>12:39 PM</td>\n",
" <td>96914</td>\n",
" <td>1.421</td>\n",
" <td>False</td>\n",
" <td>Product</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>Larry</td>\n",
" <td>Male</td>\n",
" <td>4/20/2013</td>\n",
" <td>4:45 PM</td>\n",
" <td>60500</td>\n",
" <td>11.985</td>\n",
" <td>False</td>\n",
" <td>Business Development</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>Albert</td>\n",
" <td>Male</td>\n",
" <td>5/15/2012</td>\n",
" <td>6:24 PM</td>\n",
" <td>129949</td>\n",
" <td>10.169</td>\n",
" <td>True</td>\n",
" <td>Sales</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>899 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" First Name Gender Start Date Last Login Time Salary Bonus % \\\n",
"0 Douglas Male 8/6/1993 12:42 PM 97308 6.945 \n",
"2 Maria Female 4/23/1993 11:17 AM 130590 11.858 \n",
"3 Jerry Male 3/4/2005 1:00 PM 138705 9.340 \n",
"4 Larry Male 1/24/1998 4:47 PM 101004 1.389 \n",
"5 Dennis Male 4/18/1987 1:35 AM 115163 10.125 \n",
".. ... ... ... ... ... ... \n",
"995 Henry No Gender 11/23/2014 6:09 AM 132483 16.655 \n",
"996 Phillip Male 1/31/1984 6:30 AM 42392 19.675 \n",
"997 Russell Male 5/20/2013 12:39 PM 96914 1.421 \n",
"998 Larry Male 4/20/2013 4:45 PM 60500 11.985 \n",
"999 Albert Male 5/15/2012 6:24 PM 129949 10.169 \n",
"\n",
" Senior Management Team \n",
"0 True Marketing \n",
"2 False Finance \n",
"3 True Finance \n",
"4 True Client Services \n",
"5 False Legal \n",
".. ... ... \n",
"995 False Distribution \n",
"996 False Finance \n",
"997 False Product \n",
"998 False Business Development \n",
"999 True Sales \n",
"\n",
"[899 rows x 8 columns]"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_data"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1000"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(data)"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"899"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(new_data\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"vals1 = np.array([1,np.nan,3,4])"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"nan"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"1 + np.nan"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"nan"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vals1.sum()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"nan"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vals1.min()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"nan"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vals1.max()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"8.0"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.nansum(vals1)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1.0"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.nanmin(vals1\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4.0"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.nanmax(vals1)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('log.csv')"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>time</th>\n",
" <th>user</th>\n",
" <th>video</th>\n",
" <th>playback position</th>\n",
" <th>paused</th>\n",
" <th>volume</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1469974424</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1469974454</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1469974544</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1469974574</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>10</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1469977514</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1469977544</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>1469977574</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>1469977604</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>1469974604</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>1469974694</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>14</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>1469974724</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>15</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>1469974454</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>24</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>1469974524</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>25</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>1469974424</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>23</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>1469974554</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>26</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>1469974624</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>27</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1469974654</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>28</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>1469974724</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>29</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>1469974484</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>1469974514</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>1469974754</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>30</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>1469974824</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>31</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>1469974854</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>32</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>1469974924</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>33</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>1469977424</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>1469977454</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>1469977484</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>1469977634</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>1469977664</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>1469974634</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>12</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>1469974664</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>13</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>1469977694</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>1469977724</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" time user video playback position paused volume\n",
"0 1469974424 cheryl intro.html 5 False 10.0\n",
"1 1469974454 cheryl intro.html 6 NaN NaN\n",
"2 1469974544 cheryl intro.html 9 NaN NaN\n",
"3 1469974574 cheryl intro.html 10 NaN NaN\n",
"4 1469977514 bob intro.html 1 NaN NaN\n",
"5 1469977544 bob intro.html 1 NaN NaN\n",
"6 1469977574 bob intro.html 1 NaN NaN\n",
"7 1469977604 bob intro.html 1 NaN NaN\n",
"8 1469974604 cheryl intro.html 11 NaN NaN\n",
"9 1469974694 cheryl intro.html 14 NaN NaN\n",
"10 1469974724 cheryl intro.html 15 NaN NaN\n",
"11 1469974454 sue advanced.html 24 NaN NaN\n",
"12 1469974524 sue advanced.html 25 NaN NaN\n",
"13 1469974424 sue advanced.html 23 False 10.0\n",
"14 1469974554 sue advanced.html 26 NaN NaN\n",
"15 1469974624 sue advanced.html 27 NaN NaN\n",
"16 1469974654 sue advanced.html 28 NaN 5.0\n",
"17 1469974724 sue advanced.html 29 NaN NaN\n",
"18 1469974484 cheryl intro.html 7 NaN NaN\n",
"19 1469974514 cheryl intro.html 8 NaN NaN\n",
"20 1469974754 sue advanced.html 30 NaN NaN\n",
"21 1469974824 sue advanced.html 31 NaN NaN\n",
"22 1469974854 sue advanced.html 32 NaN NaN\n",
"23 1469974924 sue advanced.html 33 NaN NaN\n",
"24 1469977424 bob intro.html 1 True 10.0\n",
"25 1469977454 bob intro.html 1 NaN NaN\n",
"26 1469977484 bob intro.html 1 NaN NaN\n",
"27 1469977634 bob intro.html 1 NaN NaN\n",
"28 1469977664 bob intro.html 1 NaN NaN\n",
"29 1469974634 cheryl intro.html 12 NaN NaN\n",
"30 1469974664 cheryl intro.html 13 NaN NaN\n",
"31 1469977694 bob intro.html 1 NaN NaN\n",
"32 1469977724 bob intro.html 1 NaN NaN"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"df = df.set_index('time')"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"df = df.sort_index()\n",
"df['date'] = pd.to_datetime(df['date'],unit='s')"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [],
"source": [
"df['time'] = pd.to_datetime(df['time'])"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>time</th>\n",
" <th>user</th>\n",
" <th>video</th>\n",
" <th>playback position</th>\n",
" <th>paused</th>\n",
" <th>volume</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1970-01-01 00:00:01.469974424</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1970-01-01 00:00:01.469974454</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1970-01-01 00:00:01.469974544</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1970-01-01 00:00:01.469974574</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>10</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1970-01-01 00:00:01.469977514</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1970-01-01 00:00:01.469977544</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>1970-01-01 00:00:01.469977574</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>1970-01-01 00:00:01.469977604</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>1970-01-01 00:00:01.469974604</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>1970-01-01 00:00:01.469974694</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>14</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>1970-01-01 00:00:01.469974724</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>15</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>1970-01-01 00:00:01.469974454</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>24</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>1970-01-01 00:00:01.469974524</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>25</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>1970-01-01 00:00:01.469974424</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>23</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>1970-01-01 00:00:01.469974554</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>26</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>1970-01-01 00:00:01.469974624</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>27</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1970-01-01 00:00:01.469974654</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>28</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>1970-01-01 00:00:01.469974724</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>29</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>1970-01-01 00:00:01.469974484</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>1970-01-01 00:00:01.469974514</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>1970-01-01 00:00:01.469974754</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>30</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>1970-01-01 00:00:01.469974824</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>31</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>1970-01-01 00:00:01.469974854</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>32</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>1970-01-01 00:00:01.469974924</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>33</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>1970-01-01 00:00:01.469977424</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>1970-01-01 00:00:01.469977454</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>1970-01-01 00:00:01.469977484</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>1970-01-01 00:00:01.469977634</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>1970-01-01 00:00:01.469977664</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>1970-01-01 00:00:01.469974634</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>12</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>1970-01-01 00:00:01.469974664</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>13</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>1970-01-01 00:00:01.469977694</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>1970-01-01 00:00:01.469977724</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" time user video playback position \\\n",
"0 1970-01-01 00:00:01.469974424 cheryl intro.html 5 \n",
"1 1970-01-01 00:00:01.469974454 cheryl intro.html 6 \n",
"2 1970-01-01 00:00:01.469974544 cheryl intro.html 9 \n",
"3 1970-01-01 00:00:01.469974574 cheryl intro.html 10 \n",
"4 1970-01-01 00:00:01.469977514 bob intro.html 1 \n",
"5 1970-01-01 00:00:01.469977544 bob intro.html 1 \n",
"6 1970-01-01 00:00:01.469977574 bob intro.html 1 \n",
"7 1970-01-01 00:00:01.469977604 bob intro.html 1 \n",
"8 1970-01-01 00:00:01.469974604 cheryl intro.html 11 \n",
"9 1970-01-01 00:00:01.469974694 cheryl intro.html 14 \n",
"10 1970-01-01 00:00:01.469974724 cheryl intro.html 15 \n",
"11 1970-01-01 00:00:01.469974454 sue advanced.html 24 \n",
"12 1970-01-01 00:00:01.469974524 sue advanced.html 25 \n",
"13 1970-01-01 00:00:01.469974424 sue advanced.html 23 \n",
"14 1970-01-01 00:00:01.469974554 sue advanced.html 26 \n",
"15 1970-01-01 00:00:01.469974624 sue advanced.html 27 \n",
"16 1970-01-01 00:00:01.469974654 sue advanced.html 28 \n",
"17 1970-01-01 00:00:01.469974724 sue advanced.html 29 \n",
"18 1970-01-01 00:00:01.469974484 cheryl intro.html 7 \n",
"19 1970-01-01 00:00:01.469974514 cheryl intro.html 8 \n",
"20 1970-01-01 00:00:01.469974754 sue advanced.html 30 \n",
"21 1970-01-01 00:00:01.469974824 sue advanced.html 31 \n",
"22 1970-01-01 00:00:01.469974854 sue advanced.html 32 \n",
"23 1970-01-01 00:00:01.469974924 sue advanced.html 33 \n",
"24 1970-01-01 00:00:01.469977424 bob intro.html 1 \n",
"25 1970-01-01 00:00:01.469977454 bob intro.html 1 \n",
"26 1970-01-01 00:00:01.469977484 bob intro.html 1 \n",
"27 1970-01-01 00:00:01.469977634 bob intro.html 1 \n",
"28 1970-01-01 00:00:01.469977664 bob intro.html 1 \n",
"29 1970-01-01 00:00:01.469974634 cheryl intro.html 12 \n",
"30 1970-01-01 00:00:01.469974664 cheryl intro.html 13 \n",
"31 1970-01-01 00:00:01.469977694 bob intro.html 1 \n",
"32 1970-01-01 00:00:01.469977724 bob intro.html 1 \n",
"\n",
" paused volume \n",
"0 False 10.0 \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"5 NaN NaN \n",
"6 NaN NaN \n",
"7 NaN NaN \n",
"8 NaN NaN \n",
"9 NaN NaN \n",
"10 NaN NaN \n",
"11 NaN NaN \n",
"12 NaN NaN \n",
"13 False 10.0 \n",
"14 NaN NaN \n",
"15 NaN NaN \n",
"16 NaN 5.0 \n",
"17 NaN NaN \n",
"18 NaN NaN \n",
"19 NaN NaN \n",
"20 NaN NaN \n",
"21 NaN NaN \n",
"22 NaN NaN \n",
"23 NaN NaN \n",
"24 True 10.0 \n",
"25 NaN NaN \n",
"26 NaN NaN \n",
"27 NaN NaN \n",
"28 NaN NaN \n",
"29 NaN NaN \n",
"30 NaN NaN \n",
"31 NaN NaN \n",
"32 NaN NaN "
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"df.sort_index()"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>user</th>\n",
" <th>video</th>\n",
" <th>playback position</th>\n",
" <th>paused</th>\n",
" <th>volume</th>\n",
" </tr>\n",
" <tr>\n",
" <th>time</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974544</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974574</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>10</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977514</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977544</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977574</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977604</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974604</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974694</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>14</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>15</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>24</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974524</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>25</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>23</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974554</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>26</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974624</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>27</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974654</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>28</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>29</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974484</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974514</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974754</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>30</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974824</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>31</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974854</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>32</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974924</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>33</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977424</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977454</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977484</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977634</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977664</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974634</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>12</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974664</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>13</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977694</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977724</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user video playback position \\\n",
"time \n",
"1970-01-01 00:00:01.469974424 cheryl intro.html 5 \n",
"1970-01-01 00:00:01.469974454 cheryl intro.html 6 \n",
"1970-01-01 00:00:01.469974544 cheryl intro.html 9 \n",
"1970-01-01 00:00:01.469974574 cheryl intro.html 10 \n",
"1970-01-01 00:00:01.469977514 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977544 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977574 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977604 bob intro.html 1 \n",
"1970-01-01 00:00:01.469974604 cheryl intro.html 11 \n",
"1970-01-01 00:00:01.469974694 cheryl intro.html 14 \n",
"1970-01-01 00:00:01.469974724 cheryl intro.html 15 \n",
"1970-01-01 00:00:01.469974454 sue advanced.html 24 \n",
"1970-01-01 00:00:01.469974524 sue advanced.html 25 \n",
"1970-01-01 00:00:01.469974424 sue advanced.html 23 \n",
"1970-01-01 00:00:01.469974554 sue advanced.html 26 \n",
"1970-01-01 00:00:01.469974624 sue advanced.html 27 \n",
"1970-01-01 00:00:01.469974654 sue advanced.html 28 \n",
"1970-01-01 00:00:01.469974724 sue advanced.html 29 \n",
"1970-01-01 00:00:01.469974484 cheryl intro.html 7 \n",
"1970-01-01 00:00:01.469974514 cheryl intro.html 8 \n",
"1970-01-01 00:00:01.469974754 sue advanced.html 30 \n",
"1970-01-01 00:00:01.469974824 sue advanced.html 31 \n",
"1970-01-01 00:00:01.469974854 sue advanced.html 32 \n",
"1970-01-01 00:00:01.469974924 sue advanced.html 33 \n",
"1970-01-01 00:00:01.469977424 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977454 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977484 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977634 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977664 bob intro.html 1 \n",
"1970-01-01 00:00:01.469974634 cheryl intro.html 12 \n",
"1970-01-01 00:00:01.469974664 cheryl intro.html 13 \n",
"1970-01-01 00:00:01.469977694 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977724 bob intro.html 1 \n",
"\n",
" paused volume \n",
"time \n",
"1970-01-01 00:00:01.469974424 False 10.0 \n",
"1970-01-01 00:00:01.469974454 NaN NaN \n",
"1970-01-01 00:00:01.469974544 NaN NaN \n",
"1970-01-01 00:00:01.469974574 NaN NaN \n",
"1970-01-01 00:00:01.469977514 NaN NaN \n",
"1970-01-01 00:00:01.469977544 NaN NaN \n",
"1970-01-01 00:00:01.469977574 NaN NaN \n",
"1970-01-01 00:00:01.469977604 NaN NaN \n",
"1970-01-01 00:00:01.469974604 NaN NaN \n",
"1970-01-01 00:00:01.469974694 NaN NaN \n",
"1970-01-01 00:00:01.469974724 NaN NaN \n",
"1970-01-01 00:00:01.469974454 NaN NaN \n",
"1970-01-01 00:00:01.469974524 NaN NaN \n",
"1970-01-01 00:00:01.469974424 False 10.0 \n",
"1970-01-01 00:00:01.469974554 NaN NaN \n",
"1970-01-01 00:00:01.469974624 NaN NaN \n",
"1970-01-01 00:00:01.469974654 NaN 5.0 \n",
"1970-01-01 00:00:01.469974724 NaN NaN \n",
"1970-01-01 00:00:01.469974484 NaN NaN \n",
"1970-01-01 00:00:01.469974514 NaN NaN \n",
"1970-01-01 00:00:01.469974754 NaN NaN \n",
"1970-01-01 00:00:01.469974824 NaN NaN \n",
"1970-01-01 00:00:01.469974854 NaN NaN \n",
"1970-01-01 00:00:01.469974924 NaN NaN \n",
"1970-01-01 00:00:01.469977424 True 10.0 \n",
"1970-01-01 00:00:01.469977454 NaN NaN \n",
"1970-01-01 00:00:01.469977484 NaN NaN \n",
"1970-01-01 00:00:01.469977634 NaN NaN \n",
"1970-01-01 00:00:01.469977664 NaN NaN \n",
"1970-01-01 00:00:01.469974634 NaN NaN \n",
"1970-01-01 00:00:01.469974664 NaN NaN \n",
"1970-01-01 00:00:01.469977694 NaN NaN \n",
"1970-01-01 00:00:01.469977724 NaN NaN "
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.set_index('time')"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>time</th>\n",
" <th>user</th>\n",
" <th>video</th>\n",
" <th>playback position</th>\n",
" <th>paused</th>\n",
" <th>volume</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1970-01-01 00:00:01.469974424</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1970-01-01 00:00:01.469974454</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1970-01-01 00:00:01.469974544</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1970-01-01 00:00:01.469974574</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>10</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1970-01-01 00:00:01.469977514</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1970-01-01 00:00:01.469977544</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>1970-01-01 00:00:01.469977574</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>1970-01-01 00:00:01.469977604</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>1970-01-01 00:00:01.469974604</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>1970-01-01 00:00:01.469974694</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>14</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>1970-01-01 00:00:01.469974724</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>15</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>1970-01-01 00:00:01.469974454</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>24</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>1970-01-01 00:00:01.469974524</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>25</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>1970-01-01 00:00:01.469974424</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>23</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>1970-01-01 00:00:01.469974554</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>26</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>1970-01-01 00:00:01.469974624</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>27</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1970-01-01 00:00:01.469974654</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>28</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>1970-01-01 00:00:01.469974724</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>29</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>1970-01-01 00:00:01.469974484</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>1970-01-01 00:00:01.469974514</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>1970-01-01 00:00:01.469974754</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>30</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>1970-01-01 00:00:01.469974824</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>31</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>1970-01-01 00:00:01.469974854</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>32</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>1970-01-01 00:00:01.469974924</td>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>33</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>1970-01-01 00:00:01.469977424</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>1970-01-01 00:00:01.469977454</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>1970-01-01 00:00:01.469977484</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>1970-01-01 00:00:01.469977634</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>1970-01-01 00:00:01.469977664</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>1970-01-01 00:00:01.469974634</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>12</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>1970-01-01 00:00:01.469974664</td>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>13</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>1970-01-01 00:00:01.469977694</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>1970-01-01 00:00:01.469977724</td>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" time user video playback position \\\n",
"0 1970-01-01 00:00:01.469974424 cheryl intro.html 5 \n",
"1 1970-01-01 00:00:01.469974454 cheryl intro.html 6 \n",
"2 1970-01-01 00:00:01.469974544 cheryl intro.html 9 \n",
"3 1970-01-01 00:00:01.469974574 cheryl intro.html 10 \n",
"4 1970-01-01 00:00:01.469977514 bob intro.html 1 \n",
"5 1970-01-01 00:00:01.469977544 bob intro.html 1 \n",
"6 1970-01-01 00:00:01.469977574 bob intro.html 1 \n",
"7 1970-01-01 00:00:01.469977604 bob intro.html 1 \n",
"8 1970-01-01 00:00:01.469974604 cheryl intro.html 11 \n",
"9 1970-01-01 00:00:01.469974694 cheryl intro.html 14 \n",
"10 1970-01-01 00:00:01.469974724 cheryl intro.html 15 \n",
"11 1970-01-01 00:00:01.469974454 sue advanced.html 24 \n",
"12 1970-01-01 00:00:01.469974524 sue advanced.html 25 \n",
"13 1970-01-01 00:00:01.469974424 sue advanced.html 23 \n",
"14 1970-01-01 00:00:01.469974554 sue advanced.html 26 \n",
"15 1970-01-01 00:00:01.469974624 sue advanced.html 27 \n",
"16 1970-01-01 00:00:01.469974654 sue advanced.html 28 \n",
"17 1970-01-01 00:00:01.469974724 sue advanced.html 29 \n",
"18 1970-01-01 00:00:01.469974484 cheryl intro.html 7 \n",
"19 1970-01-01 00:00:01.469974514 cheryl intro.html 8 \n",
"20 1970-01-01 00:00:01.469974754 sue advanced.html 30 \n",
"21 1970-01-01 00:00:01.469974824 sue advanced.html 31 \n",
"22 1970-01-01 00:00:01.469974854 sue advanced.html 32 \n",
"23 1970-01-01 00:00:01.469974924 sue advanced.html 33 \n",
"24 1970-01-01 00:00:01.469977424 bob intro.html 1 \n",
"25 1970-01-01 00:00:01.469977454 bob intro.html 1 \n",
"26 1970-01-01 00:00:01.469977484 bob intro.html 1 \n",
"27 1970-01-01 00:00:01.469977634 bob intro.html 1 \n",
"28 1970-01-01 00:00:01.469977664 bob intro.html 1 \n",
"29 1970-01-01 00:00:01.469974634 cheryl intro.html 12 \n",
"30 1970-01-01 00:00:01.469974664 cheryl intro.html 13 \n",
"31 1970-01-01 00:00:01.469977694 bob intro.html 1 \n",
"32 1970-01-01 00:00:01.469977724 bob intro.html 1 \n",
"\n",
" paused volume \n",
"0 False 10.0 \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"5 NaN NaN \n",
"6 NaN NaN \n",
"7 NaN NaN \n",
"8 NaN NaN \n",
"9 NaN NaN \n",
"10 NaN NaN \n",
"11 NaN NaN \n",
"12 NaN NaN \n",
"13 False 10.0 \n",
"14 NaN NaN \n",
"15 NaN NaN \n",
"16 NaN 5.0 \n",
"17 NaN NaN \n",
"18 NaN NaN \n",
"19 NaN NaN \n",
"20 NaN NaN \n",
"21 NaN NaN \n",
"22 NaN NaN \n",
"23 NaN NaN \n",
"24 True 10.0 \n",
"25 NaN NaN \n",
"26 NaN NaN \n",
"27 NaN NaN \n",
"28 NaN NaN \n",
"29 NaN NaN \n",
"30 NaN NaN \n",
"31 NaN NaN \n",
"32 NaN NaN "
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.sort_index()"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>user</th>\n",
" <th>video</th>\n",
" <th>playback position</th>\n",
" <th>paused</th>\n",
" <th>volume</th>\n",
" </tr>\n",
" <tr>\n",
" <th>time</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974544</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974574</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>10</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977514</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977544</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977574</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977604</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974604</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974694</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>14</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>15</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>24</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974524</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>25</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>23</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974554</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>26</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974624</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>27</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974654</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>28</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>29</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974484</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974514</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974754</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>30</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974824</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>31</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974854</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>32</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974924</th>\n",
" <td>sue</td>\n",
" <td>advanced.html</td>\n",
" <td>33</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977424</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977454</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977484</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977634</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977664</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974634</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>12</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974664</th>\n",
" <td>cheryl</td>\n",
" <td>intro.html</td>\n",
" <td>13</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977694</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977724</th>\n",
" <td>bob</td>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user video playback position \\\n",
"time \n",
"1970-01-01 00:00:01.469974424 cheryl intro.html 5 \n",
"1970-01-01 00:00:01.469974454 cheryl intro.html 6 \n",
"1970-01-01 00:00:01.469974544 cheryl intro.html 9 \n",
"1970-01-01 00:00:01.469974574 cheryl intro.html 10 \n",
"1970-01-01 00:00:01.469977514 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977544 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977574 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977604 bob intro.html 1 \n",
"1970-01-01 00:00:01.469974604 cheryl intro.html 11 \n",
"1970-01-01 00:00:01.469974694 cheryl intro.html 14 \n",
"1970-01-01 00:00:01.469974724 cheryl intro.html 15 \n",
"1970-01-01 00:00:01.469974454 sue advanced.html 24 \n",
"1970-01-01 00:00:01.469974524 sue advanced.html 25 \n",
"1970-01-01 00:00:01.469974424 sue advanced.html 23 \n",
"1970-01-01 00:00:01.469974554 sue advanced.html 26 \n",
"1970-01-01 00:00:01.469974624 sue advanced.html 27 \n",
"1970-01-01 00:00:01.469974654 sue advanced.html 28 \n",
"1970-01-01 00:00:01.469974724 sue advanced.html 29 \n",
"1970-01-01 00:00:01.469974484 cheryl intro.html 7 \n",
"1970-01-01 00:00:01.469974514 cheryl intro.html 8 \n",
"1970-01-01 00:00:01.469974754 sue advanced.html 30 \n",
"1970-01-01 00:00:01.469974824 sue advanced.html 31 \n",
"1970-01-01 00:00:01.469974854 sue advanced.html 32 \n",
"1970-01-01 00:00:01.469974924 sue advanced.html 33 \n",
"1970-01-01 00:00:01.469977424 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977454 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977484 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977634 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977664 bob intro.html 1 \n",
"1970-01-01 00:00:01.469974634 cheryl intro.html 12 \n",
"1970-01-01 00:00:01.469974664 cheryl intro.html 13 \n",
"1970-01-01 00:00:01.469977694 bob intro.html 1 \n",
"1970-01-01 00:00:01.469977724 bob intro.html 1 \n",
"\n",
" paused volume \n",
"time \n",
"1970-01-01 00:00:01.469974424 False 10.0 \n",
"1970-01-01 00:00:01.469974454 NaN NaN \n",
"1970-01-01 00:00:01.469974544 NaN NaN \n",
"1970-01-01 00:00:01.469974574 NaN NaN \n",
"1970-01-01 00:00:01.469977514 NaN NaN \n",
"1970-01-01 00:00:01.469977544 NaN NaN \n",
"1970-01-01 00:00:01.469977574 NaN NaN \n",
"1970-01-01 00:00:01.469977604 NaN NaN \n",
"1970-01-01 00:00:01.469974604 NaN NaN \n",
"1970-01-01 00:00:01.469974694 NaN NaN \n",
"1970-01-01 00:00:01.469974724 NaN NaN \n",
"1970-01-01 00:00:01.469974454 NaN NaN \n",
"1970-01-01 00:00:01.469974524 NaN NaN \n",
"1970-01-01 00:00:01.469974424 False 10.0 \n",
"1970-01-01 00:00:01.469974554 NaN NaN \n",
"1970-01-01 00:00:01.469974624 NaN NaN \n",
"1970-01-01 00:00:01.469974654 NaN 5.0 \n",
"1970-01-01 00:00:01.469974724 NaN NaN \n",
"1970-01-01 00:00:01.469974484 NaN NaN \n",
"1970-01-01 00:00:01.469974514 NaN NaN \n",
"1970-01-01 00:00:01.469974754 NaN NaN \n",
"1970-01-01 00:00:01.469974824 NaN NaN \n",
"1970-01-01 00:00:01.469974854 NaN NaN \n",
"1970-01-01 00:00:01.469974924 NaN NaN \n",
"1970-01-01 00:00:01.469977424 True 10.0 \n",
"1970-01-01 00:00:01.469977454 NaN NaN \n",
"1970-01-01 00:00:01.469977484 NaN NaN \n",
"1970-01-01 00:00:01.469977634 NaN NaN \n",
"1970-01-01 00:00:01.469977664 NaN NaN \n",
"1970-01-01 00:00:01.469974634 NaN NaN \n",
"1970-01-01 00:00:01.469974664 NaN NaN \n",
"1970-01-01 00:00:01.469977694 NaN NaN \n",
"1970-01-01 00:00:01.469977724 NaN NaN "
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.set_index('time')"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"ename": "KeyError",
"evalue": "\"None of ['time', 'user'] are in the columns\"",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-46-9d24b0e87e1c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'time'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'user'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m~/conda/envs/python/lib/python3.6/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36mset_index\u001b[0;34m(self, keys, drop, append, inplace, verify_integrity)\u001b[0m\n\u001b[1;32m 4409\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4410\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mmissing\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4411\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"None of {} are in the columns\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmissing\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4412\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4413\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0minplace\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyError\u001b[0m: \"None of ['time', 'user'] are in the columns\""
]
}
],
"source": [
"df = df.set_index(['time','user'])"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>video</th>\n",
" <th>playback position</th>\n",
" <th>paused</th>\n",
" <th>volume</th>\n",
" </tr>\n",
" <tr>\n",
" <th>time</th>\n",
" <th>user</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974544</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974574</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>10</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977514</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977544</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977574</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977604</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974604</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>11</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974694</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>14</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>15</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>24</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974524</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>25</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>23</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974554</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>26</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974624</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>27</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974654</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>28</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>29</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974484</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974514</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974754</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>30</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974824</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>31</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974854</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>32</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974924</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>33</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977424</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977454</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977484</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977634</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977664</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974634</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>12</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974664</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>13</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977694</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977724</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" video playback position paused \\\n",
"time user \n",
"1970-01-01 00:00:01.469974424 cheryl intro.html 5 False \n",
"1970-01-01 00:00:01.469974454 cheryl intro.html 6 NaN \n",
"1970-01-01 00:00:01.469974544 cheryl intro.html 9 NaN \n",
"1970-01-01 00:00:01.469974574 cheryl intro.html 10 NaN \n",
"1970-01-01 00:00:01.469977514 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469977544 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469977574 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469977604 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469974604 cheryl intro.html 11 NaN \n",
"1970-01-01 00:00:01.469974694 cheryl intro.html 14 NaN \n",
"1970-01-01 00:00:01.469974724 cheryl intro.html 15 NaN \n",
"1970-01-01 00:00:01.469974454 sue advanced.html 24 NaN \n",
"1970-01-01 00:00:01.469974524 sue advanced.html 25 NaN \n",
"1970-01-01 00:00:01.469974424 sue advanced.html 23 False \n",
"1970-01-01 00:00:01.469974554 sue advanced.html 26 NaN \n",
"1970-01-01 00:00:01.469974624 sue advanced.html 27 NaN \n",
"1970-01-01 00:00:01.469974654 sue advanced.html 28 NaN \n",
"1970-01-01 00:00:01.469974724 sue advanced.html 29 NaN \n",
"1970-01-01 00:00:01.469974484 cheryl intro.html 7 NaN \n",
"1970-01-01 00:00:01.469974514 cheryl intro.html 8 NaN \n",
"1970-01-01 00:00:01.469974754 sue advanced.html 30 NaN \n",
"1970-01-01 00:00:01.469974824 sue advanced.html 31 NaN \n",
"1970-01-01 00:00:01.469974854 sue advanced.html 32 NaN \n",
"1970-01-01 00:00:01.469974924 sue advanced.html 33 NaN \n",
"1970-01-01 00:00:01.469977424 bob intro.html 1 True \n",
"1970-01-01 00:00:01.469977454 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469977484 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469977634 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469977664 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469974634 cheryl intro.html 12 NaN \n",
"1970-01-01 00:00:01.469974664 cheryl intro.html 13 NaN \n",
"1970-01-01 00:00:01.469977694 bob intro.html 1 NaN \n",
"1970-01-01 00:00:01.469977724 bob intro.html 1 NaN \n",
"\n",
" volume \n",
"time user \n",
"1970-01-01 00:00:01.469974424 cheryl 10.0 \n",
"1970-01-01 00:00:01.469974454 cheryl NaN \n",
"1970-01-01 00:00:01.469974544 cheryl NaN \n",
"1970-01-01 00:00:01.469974574 cheryl NaN \n",
"1970-01-01 00:00:01.469977514 bob NaN \n",
"1970-01-01 00:00:01.469977544 bob NaN \n",
"1970-01-01 00:00:01.469977574 bob NaN \n",
"1970-01-01 00:00:01.469977604 bob NaN \n",
"1970-01-01 00:00:01.469974604 cheryl NaN \n",
"1970-01-01 00:00:01.469974694 cheryl NaN \n",
"1970-01-01 00:00:01.469974724 cheryl NaN \n",
"1970-01-01 00:00:01.469974454 sue NaN \n",
"1970-01-01 00:00:01.469974524 sue NaN \n",
"1970-01-01 00:00:01.469974424 sue 10.0 \n",
"1970-01-01 00:00:01.469974554 sue NaN \n",
"1970-01-01 00:00:01.469974624 sue NaN \n",
"1970-01-01 00:00:01.469974654 sue 5.0 \n",
"1970-01-01 00:00:01.469974724 sue NaN \n",
"1970-01-01 00:00:01.469974484 cheryl NaN \n",
"1970-01-01 00:00:01.469974514 cheryl NaN \n",
"1970-01-01 00:00:01.469974754 sue NaN \n",
"1970-01-01 00:00:01.469974824 sue NaN \n",
"1970-01-01 00:00:01.469974854 sue NaN \n",
"1970-01-01 00:00:01.469974924 sue NaN \n",
"1970-01-01 00:00:01.469977424 bob 10.0 \n",
"1970-01-01 00:00:01.469977454 bob NaN \n",
"1970-01-01 00:00:01.469977484 bob NaN \n",
"1970-01-01 00:00:01.469977634 bob NaN \n",
"1970-01-01 00:00:01.469977664 bob NaN \n",
"1970-01-01 00:00:01.469974634 cheryl NaN \n",
"1970-01-01 00:00:01.469974664 cheryl NaN \n",
"1970-01-01 00:00:01.469977694 bob NaN \n",
"1970-01-01 00:00:01.469977724 bob NaN "
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>video</th>\n",
" <th>playback position</th>\n",
" <th>paused</th>\n",
" <th>volume</th>\n",
" </tr>\n",
" <tr>\n",
" <th>time</th>\n",
" <th>user</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>5</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974544</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974574</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>10</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977514</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977544</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977574</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977604</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974604</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>11</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974694</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>14</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>15</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974454</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>24</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974524</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>25</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974424</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>23</td>\n",
" <td>False</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974554</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>26</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974624</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>27</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974654</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>28</td>\n",
" <td>0</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974724</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>29</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974484</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>7</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974514</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>8</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974754</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>30</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974824</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>31</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974854</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>32</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974924</th>\n",
" <th>sue</th>\n",
" <td>advanced.html</td>\n",
" <td>33</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977424</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977454</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977484</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977634</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977664</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974634</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>12</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469974664</th>\n",
" <th>cheryl</th>\n",
" <td>intro.html</td>\n",
" <td>13</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977694</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1970-01-01 00:00:01.469977724</th>\n",
" <th>bob</th>\n",
" <td>intro.html</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" video playback position paused \\\n",
"time user \n",
"1970-01-01 00:00:01.469974424 cheryl intro.html 5 False \n",
"1970-01-01 00:00:01.469974454 cheryl intro.html 6 0 \n",
"1970-01-01 00:00:01.469974544 cheryl intro.html 9 0 \n",
"1970-01-01 00:00:01.469974574 cheryl intro.html 10 0 \n",
"1970-01-01 00:00:01.469977514 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469977544 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469977574 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469977604 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469974604 cheryl intro.html 11 0 \n",
"1970-01-01 00:00:01.469974694 cheryl intro.html 14 0 \n",
"1970-01-01 00:00:01.469974724 cheryl intro.html 15 0 \n",
"1970-01-01 00:00:01.469974454 sue advanced.html 24 0 \n",
"1970-01-01 00:00:01.469974524 sue advanced.html 25 0 \n",
"1970-01-01 00:00:01.469974424 sue advanced.html 23 False \n",
"1970-01-01 00:00:01.469974554 sue advanced.html 26 0 \n",
"1970-01-01 00:00:01.469974624 sue advanced.html 27 0 \n",
"1970-01-01 00:00:01.469974654 sue advanced.html 28 0 \n",
"1970-01-01 00:00:01.469974724 sue advanced.html 29 0 \n",
"1970-01-01 00:00:01.469974484 cheryl intro.html 7 0 \n",
"1970-01-01 00:00:01.469974514 cheryl intro.html 8 0 \n",
"1970-01-01 00:00:01.469974754 sue advanced.html 30 0 \n",
"1970-01-01 00:00:01.469974824 sue advanced.html 31 0 \n",
"1970-01-01 00:00:01.469974854 sue advanced.html 32 0 \n",
"1970-01-01 00:00:01.469974924 sue advanced.html 33 0 \n",
"1970-01-01 00:00:01.469977424 bob intro.html 1 True \n",
"1970-01-01 00:00:01.469977454 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469977484 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469977634 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469977664 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469974634 cheryl intro.html 12 0 \n",
"1970-01-01 00:00:01.469974664 cheryl intro.html 13 0 \n",
"1970-01-01 00:00:01.469977694 bob intro.html 1 0 \n",
"1970-01-01 00:00:01.469977724 bob intro.html 1 0 \n",
"\n",
" volume \n",
"time user \n",
"1970-01-01 00:00:01.469974424 cheryl 10.0 \n",
"1970-01-01 00:00:01.469974454 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974544 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974574 cheryl 0.0 \n",
"1970-01-01 00:00:01.469977514 bob 0.0 \n",
"1970-01-01 00:00:01.469977544 bob 0.0 \n",
"1970-01-01 00:00:01.469977574 bob 0.0 \n",
"1970-01-01 00:00:01.469977604 bob 0.0 \n",
"1970-01-01 00:00:01.469974604 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974694 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974724 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974454 sue 0.0 \n",
"1970-01-01 00:00:01.469974524 sue 0.0 \n",
"1970-01-01 00:00:01.469974424 sue 10.0 \n",
"1970-01-01 00:00:01.469974554 sue 0.0 \n",
"1970-01-01 00:00:01.469974624 sue 0.0 \n",
"1970-01-01 00:00:01.469974654 sue 5.0 \n",
"1970-01-01 00:00:01.469974724 sue 0.0 \n",
"1970-01-01 00:00:01.469974484 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974514 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974754 sue 0.0 \n",
"1970-01-01 00:00:01.469974824 sue 0.0 \n",
"1970-01-01 00:00:01.469974854 sue 0.0 \n",
"1970-01-01 00:00:01.469974924 sue 0.0 \n",
"1970-01-01 00:00:01.469977424 bob 10.0 \n",
"1970-01-01 00:00:01.469977454 bob 0.0 \n",
"1970-01-01 00:00:01.469977484 bob 0.0 \n",
"1970-01-01 00:00:01.469977634 bob 0.0 \n",
"1970-01-01 00:00:01.469977664 bob 0.0 \n",
"1970-01-01 00:00:01.469974634 cheryl 0.0 \n",
"1970-01-01 00:00:01.469974664 cheryl 0.0 \n",
"1970-01-01 00:00:01.469977694 bob 0.0 \n",
"1970-01-01 00:00:01.469977724 bob 0.0 "
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.fillna(0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python",
"language": "python",
"name": "conda-env-python-py"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment