Codecademy export

script.py

import codecademylib3_seaborn
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

# load and investigate the data here:
df= pd.read_csv("tennis_stats.csv")
x=df[['BreakPointsOpportunities']]
y=df[['Winnings']]
print(df.head())
#plt.scatter(x,y)
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.8)
lr=LinearRegression()
lr.fit(x_train,y_train)
lr.score(x_test,y_test)
plt.scatter(x_train,y_train)
y_predict=lr.predict(x_test)
plt.plot(x_test,y_predict,color='blue',linewidth=3)
plt.show()






# perform exploratory analysis here:






















## perform single feature linear regressions here:






















## perform two feature linear regressions here:






















## perform multiple feature linear regressions here:

my first ml project on linear regression