Linear Regression.txt

import csv
import numpy as np
import pandas as pd
mydata = pd.read_csv('jobs_in_data.csv')
x = pd.DataFrame(mydata)
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

mydata.info()

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
label_encoder_x = LabelEncoder()
mydata['job_title'] = label_encoder_x.fit_transform(mydata['job_title'])

mydata['job_title']

sns.pairplot(mydata)

x = mydata[['salary']]
y = mydata['salary_in_usd']

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_state = 42)
import numpy as np
from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(x_train, y_train)

print(model.coef_)

print(model.intercept_)

pd.DataFrame(model.coef_, x.columns, columns = ['Coeff'])

predictions = model.predict(x_test)
plt.scatter(y_test, x_test, color = 'r')
plt.scatter(y_test, predictions, color='b')

plt.hist(y_test -predictions)

y_test

from sklearn import metrics

print(metrics.mean_absolute_error(y_test, predictions))
print(metrics.mean_squared_error(y_test, predictions))
print(np.sqrt(metrics.mean_squared_error(y_test, predictions)))

regressor = LinearRegression()
regressor.fit(x_train, y_train)
r2_score = regressor.score(x_test, y_test)
print(r2_score*100, '%')