Create a gist now

Instantly share code, notes, and snippets.

Embed
Correlation map of the impact of air quality on mortality rates
import pandas as pd
from sklearn.linear_model import LinearRegression
features = ['T2M']
train = pd.read_csv('./data/train.csv')
test = pd.read_csv('./data/test.csv')
train = train.dropna(axis=0, how = 'any')
print(train.describe())
X_train = train[features]
y = train['mortality_rate'].copy()
X_test = test[features].copy()
lr = LinearRegression()
lr.fit(X_train, y)
predictions = test[['Id']].copy()
predictions['mortality_rate'] = lr.predict(X_test)
predictions.to_csv('linear_regression.csv', index = False)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment