import pandas as pd
from sklearn import datasets

boston = datasets.load_boston()
df = pd.DataFrame(boston.data, columns=boston.feature_names)
df["PRICE"] = boston.target
df.head()

print(boston.DESCR)

.. _boston_dataset:

Boston house prices dataset
---------------------------

**Data Set Characteristics:**

    :Number of Instances: 506

    :Number of Attributes: 13 numeric/categorical predictive. Median Value (attribute 14) is usually the target.

    :Attribute Information (in order):
        - CRIM     per capita crime rate by town
        - ZN       proportion of residential land zoned for lots over 25,000 sq.ft.
        - INDUS    proportion of non-retail business acres per town
        - CHAS     Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)
        - NOX      nitric oxides concentration (parts per 10 million)
        - RM       average number of rooms per dwelling
        - AGE      proportion of owner-occupied units built prior to 1940
        - DIS      weighted distances to five Boston employment centres
        - RAD      index of accessibility to radial highways
        - TAX      full-value property-tax rate per $10,000
        - PTRATIO  pupil-teacher ratio by town
        - B        1000(Bk - 0.63)^2 where Bk is the proportion of black people by town
        - LSTAT    % lower status of the population
        - MEDV     Median value of owner-occupied homes in $1000's

    :Missing Attribute Values: None

    :Creator: Harrison, D. and Rubinfeld, D.L.

This is a copy of UCI ML housing dataset.
https://archive.ics.uci.edu/ml/machine-learning-databases/housing/


This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.

The Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic
prices and the demand for clean air', J. Environ. Economics & Management,
vol.5, 81-102, 1978.   Used in Belsley, Kuh & Welsch, 'Regression diagnostics
...', Wiley, 1980.   N.B. Various transformations are used in the table on
pages 244-261 of the latter.

The Boston house-price data has been used in many machine learning papers that address regression
problems.

.. topic:: References

   - Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.
   - Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(
  boston.data,
  boston.target,
  random_state=0
)

from sklearn import linear_model

x_rm_train = x_train[:, [5]]
x_rm_test = x_test[:, [5]]

model = linear_model.LinearRegression()
model.fit(x_train_rm, y_train)
a = model.coef_
b = model.intercept_
print("a: ", a)
print("b: ", b)

a:  [9.31294923]
b:  -36.180992646339206

import matplotlib.pyplot as plt

plt.scatter(x_rm_train, y_train, label="Train")
plt.scatter(x_rm_test, y_test, label="Test")

y_pred = model.predict(x_rm_train)
plt.plot(x_rm_train, y_pred, c="black")

plt.xlabel("RM")
plt.ylabel("PRICE")
plt.legend()
plt.show()

from sklearn.metrics import r2_score

y_pred_train = model.predict(x_rm_train)
print("R2 (train): ", r2_score(y_train, y_pred_train))

y_pred_test = model.predict(x_rm_test)
print("R2 (test): ", r2_score(y_test, y_pred_test))

R2 (train): 0.48752067939343646
R2 (test): 0.4679000543136781

from sklearn.metrics import mean_squared_error

print("MSE (train): ", mean_squared_error(y_train, y_pred_train))

print("MSE (test): ", mean_squared_error(y_test, y_pred_test))

MSE (train):  43.71870658739849
MSE (test):  43.472041677202206

model = linear_model.LinearRegression()

model.fit(x_train, t_train)

a_df = pd.DataFrame(boston.feature_names, columns=["Exp"])
a_df["a"] = pd.Series(model.coef_)
a_df

print("b: ", model.intercept_)

b:  36.93325545712031

from sklearn.metrics import r2_score

y_pred_train = model.predict(x_rm_train)
print("R2 (train): ", r2_score(y_train, y_pred_train))

y_pred_test = model.predict(x_rm_test)
print("R2 (test): ", r2_score(y_test, y_pred_test))

R2 (train): 0.7697699488741149
R2 (test): 0.635463843320211

from sklearn.metrics import mean_squared_error

print("MSE (train): ", mean_squared_error(y_train, y_pred_train))

print("MSE (test): ", mean_squared_error(y_test, y_pred_test))

MSE (train):  19.640519427908046
MSE (test):  29.78224509230252