#Data Preprocessing
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
dataset =pd.read_csv("studentscores.csv")
X = dataset.iloc[ : , :1].values
y = dataset.iloc[ : ,1].values
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=33)
#Fitting Simple Linear Regression Model to the training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor = regressor.fit(X_train,y_train)
#Predecting the Result
y_pred = regressor.predict(X_test)
#Visualization
#Visualising the Training results
plt.scatter(X_train,y_train,color = "red",marker='v')
plt.plot(X_train,regressor.predict(X_train),color = "blue")
#Visualizing the test results
plt.scatter(X_test,y_test,color = "orange",marker='o')
plt.plot(X_test,regressor.predict(X_test),color = "grey")
plt.legend(["y_train","y_test"])
plt.show()
dataset(studentscores.csv):
Hours,Scores
2.5,21
5.1,47
3.2,27
8.5,75
3.5,30
1.5,20
9.2,88
5.5,60
8.3,81
2.7,25
7.7,85
5.9,62
4.5,41
3.3,42
1.1,17
8.9,95
2.5,30
1.9,24
6.1,67
7.4,69
2.7,30
4.8,54
3.8,35
6.9,76
7.8,86