Skip to content

Instantly share code, notes, and snippets.

@Adhira-Deogade

Adhira-Deogade/munging

Created May 14, 2018 04:03
Show Gist options
  • Save Adhira-Deogade/a4961364395764cce4c24f48283b9290 to your computer and use it in GitHub Desktop.
Save Adhira-Deogade/a4961364395764cce4c24f48283b9290 to your computer and use it in GitHub Desktop.
Download ZIP
my gist
Raw
munging
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"from pandas import Series, DataFrame"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Selecting and retrieving data\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"row 1 0\n",
"row 2 1\n",
"row 3 2\n",
"row 4 3\n",
"row 5 4\n",
"row 6 5\n",
"row 7 6\n",
"row 8 7\n",
"dtype: int64"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_obj = Series(np.arange(8),index=['row 1','row 2','row 3','row 4','row 5','row 6','row 7','row 8'])\n",
"series_obj"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"6"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_obj['row 7']"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"row 1 0\n",
"row 8 7\n",
"dtype: int64"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_obj[[0,7]]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>column 1</th>\n",
" <th>column 2</th>\n",
" <th>column 3</th>\n",
" <th>column 4</th>\n",
" <th>column 5</th>\n",
" <th>column 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>row 1</th>\n",
" <td>0.870124</td>\n",
" <td>0.582277</td>\n",
" <td>0.278839</td>\n",
" <td>0.185911</td>\n",
" <td>0.411100</td>\n",
" <td>0.117376</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 2</th>\n",
" <td>0.684969</td>\n",
" <td>0.437611</td>\n",
" <td>0.556229</td>\n",
" <td>0.367080</td>\n",
" <td>0.402366</td>\n",
" <td>0.113041</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 3</th>\n",
" <td>0.447031</td>\n",
" <td>0.585445</td>\n",
" <td>0.161985</td>\n",
" <td>0.520719</td>\n",
" <td>0.326051</td>\n",
" <td>0.699186</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 4</th>\n",
" <td>0.366395</td>\n",
" <td>0.836375</td>\n",
" <td>0.481343</td>\n",
" <td>0.516502</td>\n",
" <td>0.383048</td>\n",
" <td>0.997541</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 5</th>\n",
" <td>0.514244</td>\n",
" <td>0.559053</td>\n",
" <td>0.034450</td>\n",
" <td>0.719930</td>\n",
" <td>0.421004</td>\n",
" <td>0.436935</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 6</th>\n",
" <td>0.281701</td>\n",
" <td>0.900274</td>\n",
" <td>0.669612</td>\n",
" <td>0.456069</td>\n",
" <td>0.289804</td>\n",
" <td>0.525819</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" column 1 column 2 column 3 column 4 column 5 column 6\n",
"row 1 0.870124 0.582277 0.278839 0.185911 0.411100 0.117376\n",
"row 2 0.684969 0.437611 0.556229 0.367080 0.402366 0.113041\n",
"row 3 0.447031 0.585445 0.161985 0.520719 0.326051 0.699186\n",
"row 4 0.366395 0.836375 0.481343 0.516502 0.383048 0.997541\n",
"row 5 0.514244 0.559053 0.034450 0.719930 0.421004 0.436935\n",
"row 6 0.281701 0.900274 0.669612 0.456069 0.289804 0.525819"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.random.seed(25)\n",
"Df_obj = DataFrame(np.random.rand(36).reshape((6,6)), index=['row 1','row 2','row 3','row 4','row 5','row 6'],\n",
" columns = ['column 1','column 2','column 3','column 4','column 5','column 6'])\n",
"Df_obj"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>column 5</th>\n",
" <th>column 2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>row 2</th>\n",
" <td>0.402366</td>\n",
" <td>0.437611</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 5</th>\n",
" <td>0.421004</td>\n",
" <td>0.559053</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" column 5 column 2\n",
"row 2 0.402366 0.437611\n",
"row 5 0.421004 0.559053"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"Df_obj.loc[['row 2', 'row 5'], ['column 5', 'column 2']]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Data Slicing\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"row 2 1\n",
"row 3 2\n",
"row 4 3\n",
"row 5 4\n",
"row 6 5\n",
"row 7 6\n",
"dtype: int64"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_obj['row 2' : 'row 7']\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Data comparison"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>column 1</th>\n",
" <th>column 2</th>\n",
" <th>column 3</th>\n",
" <th>column 4</th>\n",
" <th>column 5</th>\n",
" <th>column 6</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>row 1</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 2</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 3</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 4</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 5</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>row 6</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" column 1 column 2 column 3 column 4 column 5 column 6\n",
"row 1 False False False True False True\n",
"row 2 False False False False False True\n",
"row 3 False False True False False False\n",
"row 4 False False False False False False\n",
"row 5 False False True False False False\n",
"row 6 False False False False False False"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"Df_obj< 0.2"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Filtering with scalars"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"row 1 0\n",
"row 2 1\n",
"row 3 2\n",
"row 4 3\n",
"row 5 4\n",
"row 6 5\n",
"dtype: int64"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_obj[series_obj<6]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Setting values with scalars"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"series_obj['row 1', 'row 2', 'row 3'] = 8"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"row 1 8\n",
"row 2 8\n",
"row 3 8\n",
"row 4 3\n",
"row 5 4\n",
"row 6 5\n",
"row 7 6\n",
"row 8 7\n",
"dtype: int64"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"series_obj"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.13"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment