Skip to content

Instantly share code, notes, and snippets.

@olivx

olivx/escola.xlsx

Forked from rg3915/FromDict.ipynb
Created December 5, 2018 21:29
Show Gist options
  • Save olivx/64d657ff67ecfcc38917f5f34cc1495b to your computer and use it in GitHub Desktop.
Save olivx/64d657ff67ecfcc38917f5f34cc1495b to your computer and use it in GitHub Desktop.
Download ZIP
Annotations of Pandas DataFrame
Display the source blob
Display the rendered blob
Raw
gen_names_xlsx.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Display the source blob
Display the rendered blob
Raw
gen_random_values.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import string\n",
"# https://www.ritchieng.com/creating-dataframe-from-objects/"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'ABCDEFGHIJKLMNOPQRSTUVWXYZ'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string.ascii_uppercase"
]
},
{
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>91</td>\n",
" <td>81</td>\n",
" <td>76</td>\n",
" <td>30</td>\n",
" <td>19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>28</td>\n",
" <td>30</td>\n",
" <td>49</td>\n",
" <td>71</td>\n",
" <td>32</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>69</td>\n",
" <td>77</td>\n",
" <td>33</td>\n",
" <td>16</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>34</td>\n",
" <td>59</td>\n",
" <td>62</td>\n",
" <td>87</td>\n",
" <td>57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>93</td>\n",
" <td>64</td>\n",
" <td>50</td>\n",
" <td>33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>46</td>\n",
" <td>71</td>\n",
" <td>35</td>\n",
" <td>33</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>3</td>\n",
" <td>69</td>\n",
" <td>65</td>\n",
" <td>30</td>\n",
" <td>92</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>33</td>\n",
" <td>46</td>\n",
" <td>64</td>\n",
" <td>16</td>\n",
" <td>82</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>26</td>\n",
" <td>58</td>\n",
" <td>78</td>\n",
" <td>19</td>\n",
" <td>87</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>16</td>\n",
" <td>70</td>\n",
" <td>68</td>\n",
" <td>23</td>\n",
" <td>11</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"0 91 81 76 30 19\n",
"1 28 30 49 71 32\n",
"2 69 77 33 16 17\n",
"3 34 59 62 87 57\n",
"4 0 93 64 50 33\n",
"5 46 71 35 33 31\n",
"6 3 69 65 30 92\n",
"7 33 46 64 16 82\n",
"8 26 58 78 19 87\n",
"9 16 70 68 23 11"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"size_columns = 5\n",
"size_rows = 10\n",
"max_value = 100\n",
"_string = string.ascii_uppercase[:size_columns]\n",
"df_int = pd.DataFrame(np.random.randint(0,max_value,size=(size_rows, size_columns)), columns=list(_string))\n",
"df_int"
]
},
{
"cell_type": "code",
"execution_count": 4,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-0.556790</td>\n",
" <td>0.650430</td>\n",
" <td>-1.894784</td>\n",
" <td>-1.382816</td>\n",
" <td>1.808950</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.297879</td>\n",
" <td>0.361739</td>\n",
" <td>-1.239575</td>\n",
" <td>0.769614</td>\n",
" <td>0.574830</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.590421</td>\n",
" <td>1.447465</td>\n",
" <td>-0.868681</td>\n",
" <td>-0.105521</td>\n",
" <td>-1.796299</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.035956</td>\n",
" <td>2.398848</td>\n",
" <td>0.889333</td>\n",
" <td>1.445073</td>\n",
" <td>0.310777</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-0.035894</td>\n",
" <td>-0.801347</td>\n",
" <td>1.406680</td>\n",
" <td>1.230958</td>\n",
" <td>0.049223</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>0.338208</td>\n",
" <td>0.073445</td>\n",
" <td>1.074535</td>\n",
" <td>0.448073</td>\n",
" <td>-0.361343</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0.282894</td>\n",
" <td>-1.440926</td>\n",
" <td>-1.309745</td>\n",
" <td>-0.264459</td>\n",
" <td>-0.335074</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0.853490</td>\n",
" <td>1.519119</td>\n",
" <td>0.574555</td>\n",
" <td>1.323457</td>\n",
" <td>0.727536</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>-1.823434</td>\n",
" <td>0.010703</td>\n",
" <td>-0.550191</td>\n",
" <td>-0.639050</td>\n",
" <td>1.143485</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>0.713230</td>\n",
" <td>-0.980415</td>\n",
" <td>-1.481190</td>\n",
" <td>3.381801</td>\n",
" <td>-0.971942</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"0 -0.556790 0.650430 -1.894784 -1.382816 1.808950\n",
"1 1.297879 0.361739 -1.239575 0.769614 0.574830\n",
"2 0.590421 1.447465 -0.868681 -0.105521 -1.796299\n",
"3 0.035956 2.398848 0.889333 1.445073 0.310777\n",
"4 -0.035894 -0.801347 1.406680 1.230958 0.049223\n",
"5 0.338208 0.073445 1.074535 0.448073 -0.361343\n",
"6 0.282894 -1.440926 -1.309745 -0.264459 -0.335074\n",
"7 0.853490 1.519119 0.574555 1.323457 0.727536\n",
"8 -1.823434 0.010703 -0.550191 -0.639050 1.143485\n",
"9 0.713230 -0.980415 -1.481190 3.381801 -0.971942"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame(np.random.randn(size_rows,size_columns), columns=list(_string))\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 5,
"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>city_id</th>\n",
" <th>population</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>101</td>\n",
" <td>14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>102</td>\n",
" <td>43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>103</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>104</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>105</td>\n",
" <td>92</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>106</td>\n",
" <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>107</td>\n",
" <td>53</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>108</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>109</td>\n",
" <td>62</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" city_id population\n",
"0 100 23\n",
"1 101 14\n",
"2 102 43\n",
"3 103 4\n",
"4 104 12\n",
"5 105 92\n",
"6 106 46\n",
"7 107 53\n",
"8 108 25\n",
"9 109 62"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_dict = {\n",
" 'city_id': np.arange(100,110,1),\n",
" 'population': np.random.randint(0,101,10)\n",
"}\n",
"df_pop = pd.DataFrame(new_dict)\n",
"df_pop"
]
},
{
"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>city_id</th>\n",
" <th>population</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>10.00000</td>\n",
" <td>10.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>104.50000</td>\n",
" <td>37.400000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>3.02765</td>\n",
" <td>27.089153</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>100.00000</td>\n",
" <td>4.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>102.25000</td>\n",
" <td>16.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>104.50000</td>\n",
" <td>34.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>106.75000</td>\n",
" <td>51.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>109.00000</td>\n",
" <td>92.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" city_id population\n",
"count 10.00000 10.000000\n",
"mean 104.50000 37.400000\n",
"std 3.02765 27.089153\n",
"min 100.00000 4.000000\n",
"25% 102.25000 16.250000\n",
"50% 104.50000 34.000000\n",
"75% 106.75000 51.250000\n",
"max 109.00000 92.000000"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_pop.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Display the source blob
Display the rendered blob
Raw
import_xlsx_to_django_database.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Display the source blob
Display the rendered blob
Raw
import_xlsx_to_django_database2.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Display the source blob
Display the rendered blob
Raw
pandas.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Display the source blob
Display the rendered blob
Raw
remove_duplicated.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Display the source blob
Display the rendered blob
Raw
separe_email.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment