datafest competition 2019
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

72 lines
2.2 KiB

from sklearn import linear_model
from sklearn.preprocessing import PolynomialFeatures
import numpy as np
import pandas as pd
from sklearn.metrics import mean_squared_error, r2_score
def k_days_into_future_regression(X, y, k, n0):
"""
linear regression that returns the fitted weights as well as metrics
:param X: x timeseries dataframe (very clean, no unamed columns), multidimensional rows
:param y: y timeseries dataframe (very clean, no unamed columns), scalar rows
:param k: days predicting in advance
:param n0: ignoring the first n0 days
:return: intercept, slopes, correlation, mean squared error
"""
col = "TimeSinceAugFirst"
inp = []
out = []
for day in y[col][n0 - 1:]:
prev = day - k
xprev = X[X[col] == prev].drop(columns=[col]).to_numpy()
if xprev.shape[0] != 1:
continue
else:
xprev = xprev[0, :]
yt = y[y[col] == day].drop(columns=[col]).to_numpy()[0, :]
inp.append(xprev)
out.append(yt)
regr = linear_model.LinearRegression()
regr.fit(inp, out)
predictions = regr.predict(inp)
mse = mean_squared_error(out, predictions)/(len(out) - 2)
r2 = r2_score(out, predictions)
return regr.intercept_, regr.coef_, r2, mse
def standard_lr(x, y):
# Standard linear regression formula, gives back params and r2
regr = linear_model.LinearRegression()
regr.fit(x, y)
predictions = regr.predict(x)
mse = mean_squared_error(y, predictions) / (len(y) - 2)
r2 = r2_score(y, predictions)
return regr.intercept_, regr.coef_, r2, mse
def poly_regression(x, y, degree):
# Polynomial regression with nth degree, gives back rmse and r2
polynomial_features = PolynomialFeatures(degree=degree)
x_poly = polynomial_features.fit_transform(x)
model = linear_model.LinearRegression()
model.fit(x_poly, y)
y_poly_pred = model.predict(x_poly)
rmse = np.sqrt(mean_squared_error(y, y_poly_pred))
r2 = r2_score(y, y_poly_pred)
return rmse, r2
def main():
player = pd.read_csv("../data_preparation/cleaned/personal.csv", index_col=0)
player = player[player['playerID'] == 1]
x = player[['fatigueNorm', 'day']]
y = player['sorenessNorm']
print(standard_lr(x, y))
print(poly_regression(x, y, 5))
if __name__ == "__main__":
main()