Python - ML temperature

text = '''
2018-05-27T00:12:43Z 20 21
2018-05-27T00:17:27Z 20 22
2018-05-27T00:17:59Z 20 24
2018-05-27T00:20:01Z 20 21
2018-05-27T00:23:14Z 20 24
2018-05-28T09:39:07Z 20 22
2018-05-28T10:40:17Z 20 23
2018-05-28T20:12:47Z 20 25
2018-05-28T20:14:16Z 23 25
2018-05-30T20:29:30Z 18 24
'''

import pandas as pd
import numpy as np

data = []
for line in text.split('\n'):
    line = line.strip()
    if line:
        parts = line.split(' ')
        data.append(parts)

df = pd.DataFrame(data, columns=['datetime', 'env', 'user'])

df['datetime'] = pd.to_datetime(df['datetime'])
df['minutes'] = df['datetime'].dt.time.apply(lambda x:x.hour*60 + x.minute)
df['env']  = df['env'].astype('int')
df['user'] = df['user'].astype('int')

print(df.dtypes)
print(df)

import sklearn.linear_model
import sklearn.model_selection
import sklearn.tree

X = df[['minutes', 'env']]
y = df['user']

X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(X, y, test_size=0.2, random_state=12)

print("--- LinearRegression ---")

model = sklearn.linear_model.LinearRegression()

model.fit(X_train, y_train)

predict = model.predict(X_test)

print('diff:\n', predict - y_test)

print('MSE:', sklearn.metrics.mean_squared_error(y_test, predict))

print("--- DecisionTreeRegressor ---")

model = sklearn.tree.DecisionTreeRegressor()

model.fit(X_train, y_train)

predict = model.predict(X_test)

print('diff:\n', predict - y_test)

print('MSE:', sklearn.metrics.mean_squared_error(y_test, predict))