[wpdm_package id=’5643′]
import pandas as pd
df = pd.read_csv("./hotelpreise.csv")
df.sort_values("Stadt")
X = df[["Marge", "Quadratmeter"]].values
Y = df[["Preis in Mio EUR"]].values
X[[0, 4]]
KFold?
from sklearn.model_selection import KFold
from sklearn.linear_model import LinearRegression
kf = KFold(n_splits = 4, shuffle = True)
for train_index, test_index in kf.split(X):
print("train: " + str(train_index))
print("test: " + str(test_index))
print("-----------")
X_test = X[test_index]
X_train = X[train_index]
y_test = Y[test_index]
y_train = Y[train_index]
# Lineare Regression trainieren
model = LinearRegression()
model.fit(X_train, y_train)
print(model.score(X_test, y_test))