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')
#print(df.corr())






# perform exploratory analysis here:
#plt.scatter(df['ReturnGamesPlayed'],df['Winnings'])
#plt.scatter(df['BreakPointsFaced'],df['Wins'])
#plt.scatter(df['BreakPointsOpportunities'],df['Winnings'])
#plt.show()

model = LinearRegression()
x = df[['BreakPointsOpportunities','ReturnGamesPlayed','Aces','BreakPointsFaced','DoubleFaults','ServiceGamesPlayed','Wins','Losses']]
y = df[['Winnings']]
x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.8,test_size=0.2,random_state=3)
model.fit(x_train,y_train)
y_predict = model.predict(x_test)

plt.scatter(y_test,y_predict,alpha=0.4)
plt.xlabel("Actual Value")
plt.ylabel("Predicted Value")
#plt.plot(range(20000), range(20000))
plt.show()
print(model.score(x_train,y_train))
print(model.score(x_test,y_test))
print(model.coef_)
















## perform single feature linear regressions here:






















## perform two feature linear regressions here:






















## perform multiple feature linear regressions here: