def get_features_WI(df, min_date, city_tag, i_cols): I = get_WI_inspections(df) V, I = get_WI_violations(I) R = lib.state_yelp_reviews(df, min_date, city_tag) y, x = lib.merge_inspec_dates(I, df, R, i_cols) X = lib.summarize_reviews(x) return pd.merge(y, X, left_on=['inspec_id','business_id','id_'], right_index=True, how='inner')
def get_features_NC(df, min_date, city_tag, i_cols): I = get_NC_inspections(df) R = lib.state_yelp_reviews(df, min_date, city_tag) y, x = lib.merge_inspec_dates(I, df, R, i_cols) print y.info() X = lib.summarize_reviews(x) return pd.merge(y, X, left_on=['inspec_id','business_id','id_'], right_index=True, how='outer')
def get_features_NV(df, min_date, city_tag, i_cols):
if 'id_' not in df.columns:
df['id_'] = df.permit_number
I = get_NV_inspections(df)
R = lib.state_yelp_reviews(df, min_date, city_tag)
y, x = lib.merge_inspec_dates(I, df, R, i_cols)
X = lib.summarize_reviews(x)
return pd.merge(y, X, left_on=['inspec_id','business_id','id_'], right_index=True, how='inner')
def get_features_AZ(df, min_date, city_tag, i_cols, routine=False):
if 'id_' not in df.columns:
df['id_'] = df.permit_id
I = get_AZ_inspections(df, routine=routine)
V, I = get_AZ_violations(I)
R = lib.state_yelp_reviews(df, min_date, city_tag)
y, x = lib.merge_inspec_dates(I, df, R, i_cols)
X = lib.summarize_reviews(x)
print X.info()
return pd.merge(y, X, left_on=['inspec_id','business_id','id_'], right_index=True, how='inner')