dt_feature9.py

# Step 13

df, y, nas, mapper = proc_df(joined_samp, 'Sales', do_scale=True)
yl = np.log(y)


joined_test = joined_test.set_index("Date")

df_test, _, nas, mapper = proc_df(joined_test, 'Sales', do_scale=True, skip_flds=['Id'],
                                  mapper=mapper, na_dict=nas)

df.head(2)

# One approach is to take the last 25% of rows (sorted by date) as our validation set.

train_ratio = 0.75
# train_ratio = 0.9
train_size = int(samp_size * train_ratio); train_size
val_idx = list(range(train_size, len(df)))

val_idx = np.flatnonzero(
    (df.index<=datetime.datetime(2014,9,17)) & (df.index>=datetime.datetime(2014,8,1)))

val_idx=[0]