preproc_data

preproc_data.py

import pandas as pd
from sklearn.preprocessing import StandardScaler, MinMaxScaler
from data_info import cols_to_norm, cols_to_scale
def preproc_data(data, norm_cols=cols_to_norm, scale_cols=cols_to_scale, train_scale=None):
    """
    :param data: Dataframe
    :param norm_cols: List<string>
    :param scale_cols: List<string>
    :param train_scale: Dataframe
    :return: Tuple(Dataframe, Dataframe)
    """
    # Make a copy, not to modify original data
    new_data = data.copy()
    if train_scale is None:
        train_scale = data
    if norm_cols:
        # Normalize temp and percipation
        new_data[norm_cols] = StandardScaler().fit(train_scale[norm_cols]).transform(new_data[norm_cols])
    if scale_cols:
        # Scale year and week no but within (0,1)
        new_data[scale_cols] = MinMaxScaler(feature_range=(0, 1)).fit(train_scale[scale_cols]).transform(
            new_data[scale_cols])
    return new_data, train_scale