dt_feature82 ros fastai

dt_feature82.py

# Step 13
for v in cat_vars: joined[v] = joined[v].astype('category').cat.as_ordered()
for v in contin_vars:
    joined[v] = joined[v].fillna(0).astype('float32')
    joined_test[v] = joined_test[v].fillna(0).astype('float32')
    
dep = 'Sales'
joined = joined[cat_vars+contin_vars+[dep, 'Date']].copy()


# We're going to run on a sample.    
idxs = get_cv_idxs(n, val_pct=150000/n)
joined_samp = joined.iloc[idxs].set_index("Date")
samp_size = len(joined_samp); samp_size
# 150000

# To run on the full dataset, use this instead:
samp_size = n
joined_samp = joined.set_index("Date")