```python
import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import scipy
from scipy.stats import ttest_ind
print("Pandas version: {}".format(pd.__version__))
print("Numpy version: {}".format(np.__version__))
print("Seaborn version: {}".format(sns.__version__))
print("Scipy version: {}".format(scipy.__version__))
print("Matplotlib version: {}".format(matplotlib.__version__))
```
Pandas version: 2.2.2
Numpy version: 1.26.4
Seaborn version: 0.13.2
Scipy version: 1.13.1
Matplotlib version: 3.9.2
```python
df = sns.load_dataset('tips')
df.head()
```
<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>total_bill</th>
<th>tip</th>
<th>sex</th>
<th>smoker</th>
<th>day</th>
<th>time</th>
<th>size</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>16.99</td>
<td>1.01</td>
<td>Female</td>
<td>No</td>
<td>Sun</td>
<td>Dinner</td>
<td>2</td>
</tr>
<tr>
<th>1</th>
<td>10.34</td>
<td>1.66</td>
<td>Male</td>
<td>No</td>
<td>Sun</td>
<td>Dinner</td>
<td>3</td>
</tr>
<tr>
<th>2</th>
<td>21.01</td>
<td>3.50</td>
<td>Male</td>
<td>No</td>
<td>Sun</td>
<td>Dinner</td>
<td>3</td>
</tr>
<tr>
<th>3</th>
<td>23.68</td>
<td>3.31</td>
<td>Male</td>
<td>No</td>
<td>Sun</td>
<td>Dinner</td>
<td>2</td>
</tr>
<tr>
<th>4</th>
<td>24.59</td>
<td>3.61</td>
<td>Female</td>
<td>No</td>
<td>Sun</td>
<td>Dinner</td>
<td>4</td>
</tr>
</tbody>
</table>
</div>
# TTest_ind
HO : "il n'y a pas de différence entre le pourboire moyen laissé par les hommes et par les femmes"
```python
df.groupby("sex")["tip"].describe()
```
/tmp/ipykernel_17513/199809758.py:1: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
df.groupby("sex")["tip"].describe()
<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>count</th>
<th>mean</th>
<th>std</th>
<th>min</th>
<th>25%</th>
<th>50%</th>
<th>75%</th>
<th>max</th>
</tr>
<tr>
<th>sex</th>
<th></th>
<th></th>
<th></th>
<th></th>
<th></th>
<th></th>
<th></th>
<th></th>
</tr>
</thead>
<tbody>
<tr>
<th>Male</th>
<td>157.0</td>
<td>3.089618</td>
<td>1.489102</td>
<td>1.0</td>
<td>2.0</td>
<td>3.00</td>
<td>3.76</td>
<td>10.0</td>
</tr>
<tr>
<th>Female</th>
<td>87.0</td>
<td>2.833448</td>
<td>1.159495</td>
<td>1.0</td>
<td>2.0</td>
<td>2.75</td>
<td>3.50</td>
<td>6.5</td>
</tr>
</tbody>
</table>
</div>
```python
df_male = df.query("`sex` == 'Male'")
df_female = df.query("`sex` == 'Female'")
```
```python
ttest_ind(df_male["tip"], df_female["tip"])
```
TtestResult(statistic=1.387859705421269, pvalue=0.16645623503456755, df=242.0)
# En résumé
```python
print(f"H0 :\"il n'y a pas de différence entre le pourboire moyen laissé par les hommes et par les femmes\"")
print()
alpha = 0.02
p_value = ttest_ind(df_male["tip"], df_female["tip"]).pvalue
if p_value < alpha:
print("Nous avons suffisamment d'éléments pour rejeter H0")
else:
print("Nous n'avons pas suffisamment d'éléments pour rejeter H0")
```
H0 :"il n'y a pas de différence entre le pourboire moyen laissé par les hommes et par les femmes"
Nous n'avons pas suffisamment d'éléments pour rejeter H0