In the previous step, we split the bikesData into Training data set (train_set) and Test data set (test_set), but can we use this 'Training' data set as it is, or, we need to do some more refinement before we can use it to generate ML models?
Yes, you got it right, we need to create target data set, and also, we need to create a final 'Training' data set by dropping the target label from the existing 'Training' data set (train_set).
Import following from scikit-learn:
cross_val_score
cross_val_predict
DecisionTreeRegressor
LinearRegression
RandomForestRegressor
Import XGBRegressor from xgboost
Create a dataframe called trainingCols by dropping cnt column data from train_set data frame.
Extract cnt column data from train_set dataframe and store it in trainingLabels variable.
Loading comments...