Housing_price_regression

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

import warnings
warnings.filterwarnings("ignore")

df = pd.read_csv("https://raw.githubusercontent.com/yoonkt200/FastCampusDataset/master/BostonHousing2.csv")

df.head()

df.shape

df.isnull().sum()

df.info()

df['CMEDV'].describe()

df['CMEDV'].hist(bins = 50)

df.boxplot(column = ['CMEDV'])

numerical_columns = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT' ]
fig = plt.figure(figsize = (16,20))
ax = fig.gca()

df[numerical_columns].hist(ax = ax)
plt.show()

cols = ['CMEDV', 'CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT' ]
corr = df[cols].corr(method = 'pearson')

corr

fig = plt.figure(figsize = (16, 20))
ax = fig.gca()

sns.set(font_scale = 1.5)
hm = sns.heatmap(corr.values, annot = True, fmt = '.2f', annot_kws = {'size' : 15}, yticklabels = cols, xticklabels = cols, ax =ax)
plt.tight_layout()
plt.show()

plt.plot('RM', 'CMEDV', data = df, linestyle = 'none', marker = 'o', markersize = 5, color = 'blue', alpha = 0.5)
plt.title("Scatter plot")
plt.xlabel('RM')
plt.ylabel('CM')
plt.show()

plt.plot('RM', 'LSTAT', data = df, linestyle = 'none', marker = 'o', markersize = 5, color = 'blue', alpha = 0.5)
plt.title("Scatter plot")
plt.xlabel('RM')
plt.ylabel('CM')
plt.show()

df['TOWN'].value_counts()

df['TOWN'].value_counts().hist(bins = 50)

fig = plt.figure(figsize = (12, 20))
ax = fig.gca()
sns.boxplot(x = 'CMEDV', y = 'TOWN', data = df, ax = ax)

fig = plt.figure(figsize = (12, 20))
ax = fig.gca()
sns.boxplot(x = 'CRIM', y = 'TOWN', data = df, ax = ax)

df.head()

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
scale_columns = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT' ]
df[scale_columns] = scaler.fit_transform(df[scale_columns])

df.head()

from sklearn.model_selection import train_test_split

X = df[scale_columns]
y = df['CMEDV']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 33)

X_train.shape, X_test.shape

from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from math import sqrt

lr = LinearRegression()
model = lr.fit(X_train, y_train)

print(lr.coef_)

plt.rcParams['figure.figsize'] = [12, 6]
coefs = lr.coef_.tolist()
coefs_series = pd.Series(coefs)

x_labels = scale_columns
ax = coefs_series.plot.barh()
ax.set_title('feature coef graph')
ax.set_xlabel('coef')
ax.set_ylabel('x_features')
ax.set_yticklabels(x_labels)
plt.show()

print(model.score(X_train, y_train))

print(model.score(X_test, y_test))

predict = lr.predict(X_train)
print(sqrt(mean_squared_error(y_train, predict)))

predict = lr.predict(X_test)
print(sqrt(mean_squared_error(y_test, predict)))

import statsmodels.api as sm

X_train = sm.add_constant(X_train)
model = sm.OLS(y_train, X_train).fit()
model.summary()

from statsmodels.stats.outliers_influence import variance_inflation_factor

vif = pd.DataFrame()
vif['VIF Factor'] = [variance_inflation_factor(X_train.values, i) for i in range(X_train.shape[1])]

vif.head()

vif['feature'] = X_train.columns

vif.round(1)