House-price-prediction

import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import re from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error from sklearn.datasets import load_boston from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression

boston_dataset = load_boston() print(boston_dataset.DESCR)

df = pd.DataFrame(boston_dataset.data, columns=boston_dataset.feature_names) df['MEDV'] = boston_dataset.target

df.shape

df.dtypes

df.columns.unique()

df.nunique()

df.isnull().sum()

df.describe()

df.corr

plt.figure(figsize=(10,10)) sns.heatmap(data=df.corr(), annot=True)

# sns.pairplot(df, size=2.5)

#Plot a box plot plt.figure(figsize=(20,20)) df.boxplot()

# Minimum price df.MEDV.min()

#Maximum price df.MEDV.max()

# standard deviation df.MEDV.std()

x =np.array(df.drop('MEDV', axis=1)) y =np.array(df.MEDV)

x_train , x_test , y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)

len(x_train)

len(y_train)

len(x_test)

len(y_test)

model = LinearRegression()

model.fit(x_train, y_train)

model.intercept_

model.coef_

y_pred = model.predict(x_test)

y_pred

model.score(x_test, y_test)

r2_score(y_test, y_pred)

mean_squared_error(y_test, y_pred)

mean_absolute_error(y_test, y_pred)

plt.scatter(y_test, y_pred) plt.xlabel("actual price") plt.ylabel("Predicted price") plt.grid() plt.plot([min(y_test), max(y_test)], [min(y_pred), max(y_pred)], color='red') plt.title("Actual v/s Predicted price")

import klib from sklearn.datasets import load_diabetes, load_iris

df2 = pd.read_csv('/work/train.csv') # df.columns =load_iris().feature_names

df2

klib.cat_plot(df2)

klib.dist_plot(df2)

import joblib

joblib.dump(model, 'house_price_model.pkl')

CRIM

INDUS

CHAS

NOX

AGE

DIS

RAD

TAX

PTRATIO

LSTAT