قیمت خانه با 81 فیچر- قسمت اول

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
## Display all the columns of the dataframe

pd.pandas.set_option('display.max_columns',None)

dataset=pd.read_csv('house_advance_train.csv')
print(dataset.shape)

features_with_na=[features for features in dataset.columns if dataset[features].isnull().sum()>1]

for feature in features_with_na:
    print(feature,'---->', np.round(dataset[feature].isnull().mean(), 4),  ' % missing values')

for feature in features_with_na:
    data = dataset.copy()
    
    # let's make a variable that indicates 1 if the observation was missing or zero otherwise
    data[feature] = np.where(data[feature].isnull(), 1, 0)
   
    # let's calculate the mean SalePrice where the information is missing or present
    data.groupby(feature)['SalePrice'].median().plot.bar()
    plt.title(feature)
    plt.show()

# list of numerical variables
numerical_features = [feature for feature in dataset.columns if dataset[feature].dtypes != 'O']

print('Number of numerical variables: ', len(numerical_features))

# visualise the numerical variables
dataset[numerical_features].head()

# list of variables that contain year information
year_feature = [feature for feature in numerical_features if 'Yr' in feature or 'Year' in feature]

year_feature

figure, axis = plt.subplots(2, 2)

axis[0, 0].plot(dataset.groupby('YrSold')['SalePrice'].median())
axis[0, 0].set_title("YrSold")

axis[0, 1].plot(dataset.groupby('YearBuilt')['SalePrice'].median())
axis[0, 1].set_title("YearBuilt")

axis[1, 0].plot(dataset.groupby('YearRemodAdd')['SalePrice'].median())
axis[1, 0].set_title("YearRemodAdd")

axis[1, 1].plot(dataset.groupby('GarageYrBlt')['SalePrice'].median())
axis[1, 1].set_title("GarageYrBlt")



plt.show()

for feature in year_feature:
    if feature!='YrSold':
        data=dataset.copy()
        ## We will capture the difference between year variable and year the house was sold for
        data[feature]=data['YrSold']-data[feature]

        plt.scatter(data[feature],data['SalePrice'])
        plt.xlabel(feature)
        plt.ylabel('SalePrice')
        plt.show()

## Numerical variables are usually of 2 type
## 1. Continous variable and Discrete Variables

discrete_feature=[feature for feature in numerical_features if \
                  len(dataset[feature].unique())<25 and \
                  feature not in year_feature+['Id']]

print("Discrete Variables Count: {}".format(len(discrete_feature)))

## Lets Find the realtionship between them and Sale PRice

for feature in discrete_feature:
    data=dataset.copy()
    data.groupby(feature)['SalePrice'].median().plot.bar()
    plt.xlabel(feature)
    plt.ylabel('SalePrice')
    plt.title(feature)
    plt.show()

continuous_feature=[feature for feature in numerical_features if feature not in discrete_feature+year_feature+['Id']]
print("Continuous feature Count {}".format(len(continuous_feature)))

## Lets analyse the continuous values by creating histograms to understand the distribution

for feature in continuous_feature:
    data=dataset.copy()
    data[feature].hist(bins=25)
    plt.xlabel(feature)
    plt.ylabel("Count")
    plt.title(feature)
    plt.show()