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:
tennis=pd.read_csv('tennis_stats.csv')
print(tennis.head())

#check correlation
plt.scatter(tennis['BreakPointsOpportunities'],tennis['Wins'],alpha=0.4)
plt.show()
print(tennis.corr())

#feature of FirstServeReturnPointsWon
features = tennis[['FirstServeReturnPointsWon']]
outcome = tennis[['Winnings']]

features_train, features_test, outcome_train, outcome_test = train_test_split(features, outcome, train_size = 0.8)

model = LinearRegression()
model.fit(features_train,outcome_train)

model.score(features_test,outcome_test)

prediction = model.predict(features_test)
plt.scatter(outcome_test,prediction, alpha=0.4)
plt.show()

#feature of BreakPointsOpportunities
features = tennis[['BreakPointsOpportunities']]
outcome = tennis[['Winnings']]

features_train, features_test, outcome_train, outcome_test = train_test_split(features, outcome, train_size = 0.8)

model = LinearRegression()
model.fit(features_train,outcome_train)

model.score(features_test,outcome_test)

prediction = model.predict(features_test)
plt.scatter(outcome_test,prediction, alpha=0.4)
plt.show()

#features of BreakPointsOpportunities,FirstServeReturnPointsWon
features = tennis[['BreakPointsOpportunities',
'FirstServeReturnPointsWon']]
outcome = tennis[['Winnings']]

features_train, features_test, outcome_train, outcome_test = train_test_split(features, outcome, train_size = 0.8)

model = LinearRegression()
model.fit(features_train,outcome_train)

print(model.score(features_test,outcome_test))

prediction = model.predict(features_test)
plt.scatter(outcome_test,prediction, alpha=0.4)
plt.show()

# perform exploratory analysis here:
features = tennis[['FirstServe','FirstServePointsWon','FirstServeReturnPointsWon',
'SecondServePointsWon','SecondServeReturnPointsWon','Aces',
'BreakPointsConverted','BreakPointsFaced','BreakPointsOpportunities',
'BreakPointsSaved','DoubleFaults','ReturnGamesPlayed','ReturnGamesWon',
'ReturnPointsWon','ServiceGamesPlayed','ServiceGamesWon','TotalPointsWon',
'TotalServicePointsWon']]
outcome = tennis[['Winnings']]

features_train, features_test, outcome_train, outcome_test = train_test_split(features, outcome, train_size = 0.8)

model = LinearRegression()
model.fit(features_train,outcome_train)

print(model.score(features_test,outcome_test))

prediction = model.predict(features_test)
plt.scatter(outcome_test,prediction, alpha=0.4)
plt.show()



















## perform single feature linear regressions here:






















## perform two feature linear regressions here:






















## perform multiple feature linear regressions here: