ium_444421/preparation.py

#!/usr/bin/env python
# coding: utf-8

# In[ ]:


# get_ipython().system('kaggle datasets download -d tejashvi14/travel-insurance-prediction-data')


# In[ ]:


get_ipython().system('unzip -o travel-insurance-prediction-data.zip')


# In[5]:


import pandas as pd
travel_insurance=pd.read_csv('TravelInsurancePrediction.csv', index_col=0)
travel_insurance


# In[ ]:


# usunięcie wierszy zawierających braki
travel_insurance.dropna(axis='index', how='any')


# In[6]:


# normalizacja danych
for column in travel_insurance.columns:
    if travel_insurance[column].dtype == 'object':
        travel_insurance[column] = travel_insurance[column].str.lower()

travel_insurance


# In[8]:


# podział na podzbiory train/dev/test
import sklearn
from sklearn.model_selection import train_test_split
travel_insurance_train, travel_insurance_rest = sklearn.model_selection.train_test_split(travel_insurance, test_size=0.4, random_state=1)
travel_insurance_test, travel_insurance_dev = sklearn.model_selection.train_test_split(travel_insurance_rest, test_size=0.5, random_state=1)


# In[27]:


travel_insurance.describe(include='all')


# In[23]:


# zwracanie informacji o danym zbiorze 

import seaborn as sns

def printInformation(data):
    print(f'Size (rows): {len(data)}\n')
    mean_value = data.mean()
    min_value = data.min(numeric_only=True)
    max_value = data.max(numeric_only=True)
    std_value = data.std()
    median_value = data.median()
    print(f'(mean)\n{mean_value}', f'(min)\n{min_value}', f'(max)\n{max_value}', f'(std)\n{std_value}', f'(median)\n{median_value}', sep="\n\n")
    sns.pairplot(data=data, hue="TravelInsurance")


# In[24]:


printInformation(travel_insurance)


# In[11]:


printInformation(travel_insurance_train)


# In[12]:


printInformation(travel_insurance_test)


# In[13]:


printInformation(travel_insurance_dev)


# In[ ]: