build_regr_model.py

import numpy as np
import pandas as pd
from sklearn import linear_model
import sklearn.metrics as sm
import matplotlib.pyplot as plt

# Importing the dataset
dataset = pd.read_csv(r'D:\computer_vision\data\salary_data.csv')
X = dataset.iloc[:, :-1].values #get a copy of dataset exclude last column
y = dataset.iloc[:, 1].values #get array of dataset in column 1st

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=0)
# Fitting Simple Linear Regression to the Training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
# regressor.fit(X_train, y_train)
regressor.fit(X_train.reshape(-1, 1), y_train)


# Visualizing the Training set results
viz_train = plt
viz_train.scatter(X_train, y_train, color='red')
viz_train.plot(X_train, regressor.predict(X_train), color='blue')
viz_train.title('Salary VS Experience (Training set)')
viz_train.xlabel('Year of Experience')
viz_train.ylabel('Salary')
viz_train.show()

# Visualizing the Test set results
viz_test = plt
viz_test.scatter(X_test, y_test, color='red')
viz_test.plot(X_train, regressor.predict(X_train), color='blue')
viz_test.title('Salary VS Experience (Test set)')
viz_test.xlabel('Year of Experience')
viz_test.ylabel('Salary')
viz_test.show()


# # Predicting the result of 5 Years Experience
y_pred = regressor.predict(([[5]]))
print(y_pred)

# Predicting the Test set results
y_pred = regressor.predict(X_test)
print(y_pred)




# Multi regressor
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model, metrics

boston = datasets.load_boston(return_X_y=False)
X = boston.data
y = boston.target

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.7, random_state=1)



reg = linear_model.LinearRegression()
reg.fit(X_train, y_train)
print('Coefficients: \n', reg.coef_)
print('Variance score: {}'.format(reg.score(X_test, y_test)))
plt.style.use('fivethirtyeight')
plt.scatter(reg.predict(X_train), reg.predict(X_train) - y_train,
   color = "green", s = 10, label = 'Train data')
plt.scatter(reg.predict(X_test), reg.predict(X_test) - y_test,
   color = "blue", s = 10, label = 'Test data')
plt.hlines(y = 0, xmin = 0, xmax = 50, linewidth = 2)
plt.legend(loc = 'upper right')
plt.title("Residual errors")
plt.show()