Chenhui/code improvments (#157)

* updated docstring

* pinged package versions

* minor improvements

* minor improvement

Former-commit-id: 43a423eacf

fclib/fclib/dataset/ojdata.py

@@ -420,7 +420,7 @@ def specify_retail_data_schema(
         df (Pandas DataFrame): sales data combined with store demographic features
     """
     # Read the 1st split of training data if "sales" is not specified
-    if sales is None:
+    if not sales:
         print("Sales dataframe is not given! The 1st split of training data will be used.")
         sales = pd.read_csv(os.path.join(data_dir, "train", "train_round_1.csv"), index_col=False)
         aux = pd.read_csv(os.path.join(data_dir, "train", "aux_round_1.csv"), index_col=False)

fclib/fclib/feature_engineering/feature_utils.py

@@ -61,7 +61,7 @@ def day_type(datetime_col, holiday_col=None, semi_holiday_offset=timedelta(days=
     datetype = pd.DataFrame({"DayType": datetime_col.dt.dayofweek})
     datetype.replace({"DayType": WEEK_DAY_TYPE_MAP}, inplace=True)
 
-    if holiday_col is not None:
+    if holiday_col:
         holiday_mask = holiday_col > 0
         datetype.loc[holiday_mask, "DayType"] = HOLIDAY_CODE
 
@@ -606,7 +606,7 @@ def same_day_hour_moving_average(
         week_lag_start = start_week + i
         hour_lags = [(week_lag_start + w) * 24 * 7 for w in range(window_size)]
         hour_lags = [h for h in hour_lags if h > max_diff]
-        if len(hour_lags) > 0:
+        if hour_lags:
             tmp_df = df[["value"]].copy()
             tmp_col_all = []
             for h in hour_lags:
@@ -678,7 +678,7 @@ def same_day_hour_moving_quantile(
         week_lag_start = start_week + i
         hour_lags = [(week_lag_start + w) * 24 * 7 for w in range(window_size)]
         hour_lags = [h for h in hour_lags if h > max_diff]
-        if len(hour_lags) > 0:
+        if hour_lags:
             tmp_df = df[["value"]].copy()
             tmp_col_all = []
             for h in hour_lags:
@@ -749,7 +749,7 @@ def same_day_hour_moving_std(
         week_lag_start = start_week + i
         hour_lags = [(week_lag_start + w) * 24 * 7 for w in range(window_size)]
         hour_lags = [h for h in hour_lags if h > max_diff]
-        if len(hour_lags) > 0:
+        if hour_lags:
             tmp_df = df[["value"]].copy()
             tmp_col_all = []
             for h in hour_lags:
@@ -825,7 +825,7 @@ def same_day_hour_moving_agg(
         week_lag_start = start_week + i
         hour_lags = [(week_lag_start + w) * 24 * 7 for w in range(window_size)]
         hour_lags = [h for h in hour_lags if h > max_diff]
-        if len(hour_lags) > 0:
+        if hour_lags:
             tmp_df = df[["value"]].copy()
             tmp_col_all = []
             for h in hour_lags:

fclib/requirements.txt

@@ -1,5 +1,5 @@
-pandas
-datetime
-scikit_learn
-numpy
-requests
+pandas==0.23.4
+datetime==4.3
+scikit-learn==0.20.3
+numpy==1.16.2
+requests==2.23.0

tools/environment.yml

@@ -1,11 +1,11 @@
 # Copyright (c) Microsoft Corporation.
-# Licensed under the MIT License. 
+# Licensed under the MIT License.
 
 # To create the conda environment:
-# $ conda env create -f environment.yaml
+# $ conda env create -f environment.yml
 #
 # To update the conda environment:
-# $ conda env update -f environment.yaml
+# $ conda env update -f environment.yml
 #
 # To register the conda environment in Jupyter:
 # $ conda activate forecasting_env