206 lines
7.1 KiB
Plaintext
206 lines
7.1 KiB
Plaintext
|
{
|
||
|
"cells": [
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"# Données manquantes\n",
|
||
|
"\n",
|
||
|
"Montrons quelques méthodes pratiques pour traiter les données manquantes dans pandas :"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 1,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"import numpy as np\n",
|
||
|
"import pandas as pd"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 2,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"df = pd.DataFrame({'A':[1,2,np.nan],\n",
|
||
|
" 'B':[5,np.nan,np.nan],\n",
|
||
|
" 'C':[1,2,3]})"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 3,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"output_type": "execute_result",
|
||
|
"data": {
|
||
|
"text/plain": [
|
||
|
" A B C\n",
|
||
|
"0 1.0 5.0 1\n",
|
||
|
"1 2.0 NaN 2\n",
|
||
|
"2 NaN NaN 3"
|
||
|
],
|
||
|
"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 </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1.0</td>\n <td>5.0</td>\n <td>1</td>\n </tr>\n <tr>\n <th>1</th>\n <td>2.0</td>\n <td>NaN</td>\n <td>2</td>\n </tr>\n <tr>\n <th>2</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>3</td>\n </tr>\n </tbody>\n</table>\n</div>"
|
||
|
},
|
||
|
"metadata": {},
|
||
|
"execution_count": 3
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 4,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"output_type": "execute_result",
|
||
|
"data": {
|
||
|
"text/plain": [
|
||
|
" A B C\n",
|
||
|
"0 1.0 5.0 1"
|
||
|
],
|
||
|
"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 </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1.0</td>\n <td>5.0</td>\n <td>1</td>\n </tr>\n </tbody>\n</table>\n</div>"
|
||
|
},
|
||
|
"metadata": {},
|
||
|
"execution_count": 4
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df.dropna()"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 5,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"output_type": "execute_result",
|
||
|
"data": {
|
||
|
"text/plain": [
|
||
|
" C\n",
|
||
|
"0 1\n",
|
||
|
"1 2\n",
|
||
|
"2 3"
|
||
|
],
|
||
|
"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>C</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1</td>\n </tr>\n <tr>\n <th>1</th>\n <td>2</td>\n </tr>\n <tr>\n <th>2</th>\n <td>3</td>\n </tr>\n </tbody>\n</table>\n</div>"
|
||
|
},
|
||
|
"metadata": {},
|
||
|
"execution_count": 5
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df.dropna(axis=1)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 6,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"output_type": "execute_result",
|
||
|
"data": {
|
||
|
"text/plain": [
|
||
|
" A B C\n",
|
||
|
"0 1.0 5.0 1\n",
|
||
|
"1 2.0 NaN 2"
|
||
|
],
|
||
|
"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 </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1.0</td>\n <td>5.0</td>\n <td>1</td>\n </tr>\n <tr>\n <th>1</th>\n <td>2.0</td>\n <td>NaN</td>\n <td>2</td>\n </tr>\n </tbody>\n</table>\n</div>"
|
||
|
},
|
||
|
"metadata": {},
|
||
|
"execution_count": 6
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df.dropna(thresh=2)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 7,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"output_type": "execute_result",
|
||
|
"data": {
|
||
|
"text/plain": [
|
||
|
" A B C\n",
|
||
|
"0 1 5 1\n",
|
||
|
"1 2 Valeur de remplacement 2\n",
|
||
|
"2 Valeur de remplacement Valeur de remplacement 3"
|
||
|
],
|
||
|
"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 </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1</td>\n <td>5</td>\n <td>1</td>\n </tr>\n <tr>\n <th>1</th>\n <td>2</td>\n <td>Valeur de remplacement</td>\n <td>2</td>\n </tr>\n <tr>\n <th>2</th>\n <td>Valeur de remplacement</td>\n <td>Valeur de remplacement</td>\n <td>3</td>\n </tr>\n </tbody>\n</table>\n</div>"
|
||
|
},
|
||
|
"metadata": {},
|
||
|
"execution_count": 7
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df.fillna(value='Valeur de remplacement')"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 8,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"output_type": "execute_result",
|
||
|
"data": {
|
||
|
"text/plain": [
|
||
|
"0 1.0\n",
|
||
|
"1 2.0\n",
|
||
|
"2 1.5\n",
|
||
|
"Name: A, dtype: float64"
|
||
|
]
|
||
|
},
|
||
|
"metadata": {},
|
||
|
"execution_count": 8
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"df['A'].fillna(value=df['A'].mean())"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"# Bon travail!"
|
||
|
]
|
||
|
}
|
||
|
],
|
||
|
"metadata": {
|
||
|
"kernelspec": {
|
||
|
"name": "python3",
|
||
|
"display_name": "Python 3.7.9 64-bit ('pyfinance': conda)",
|
||
|
"metadata": {
|
||
|
"interpreter": {
|
||
|
"hash": "e89404a230d8800c54ad520c7b67d1bd9bb833a07b37dd3e521a178a3dc34904"
|
||
|
}
|
||
|
}
|
||
|
},
|
||
|
"language_info": {
|
||
|
"codemirror_mode": {
|
||
|
"name": "ipython",
|
||
|
"version": 3
|
||
|
},
|
||
|
"file_extension": ".py",
|
||
|
"mimetype": "text/x-python",
|
||
|
"name": "python",
|
||
|
"nbconvert_exporter": "python",
|
||
|
"pygments_lexer": "ipython3",
|
||
|
"version": "3.7.9-final"
|
||
|
}
|
||
|
},
|
||
|
"nbformat": 4,
|
||
|
"nbformat_minor": 1
|
||
|
}
|