Make parse_profile_features into proper function

src/data/profile_features.py

@@ -13,7 +13,7 @@ from shapely.ops import transform
 
 def shapes_from_shp(shp_file):
     """
-    Parses a shape file and returns a list of shapely shapes
+    Parses a shape file and returns a list of shapely shapes, ids and properties
     :param shp_file:
     :return:
     """
@@ -158,27 +158,23 @@ def beach_profile_elevation(x_coord, df_profiles, profile_type, site_id):
     return np.interp(x_coord, df_profile.index.get_level_values('x'), df_profile['z'])
 
 
-# todo
-def get_sites_dune_crest_toe():
+def parse_profile_features(df_sites, df_profiles, dune_crest_shp, dune_toe_shp):
     """
-    Reads dune crest and toe files and creates a pandas dataframe with crest/toe locations at each site_
+    Reads dune crest and toe files and creates a pandas dataframe with crest/toe locations at each site
     :return:
     """
 
     # Get site information. Base our profile features on each site
-    data_folder = './data/interim'
-    df_sites = pd.read_csv(os.path.join(data_folder, 'sites.csv'), index_col=[0])
-    df_profiles = pd.read_csv(os.path.join(data_folder, 'profiles.csv'), index_col=[0, 1, 2])
     df_profile_features = df_sites
 
     features = {
         'dune_crest':
             {
-                'file': './data/raw/profile_features/dune_crests.shp'
+                'file': dune_crest_shp
             },
         'dune_toe':
             {
-                'file': './data/raw/profile_features/dune_toes.shp'
+                'file': dune_toe_shp
             },
     }
 
@@ -207,5 +203,15 @@ def get_sites_dune_crest_toe():
                                                                   axis=1)
 
     df_profile_features = df_profile_features.drop(columns=['beach', 'lat', 'lon', 'orientation'])
-    df_profile_features.to_csv('./data/interim/profile_features.csv')
+    return df_profile_features
+
 
+if __name__ == '__main__':
+    data_folder = './data/interim'
+    df_sites = pd.read_csv(os.path.join(data_folder, 'sites.csv'), index_col=[0])
+    df_profiles = pd.read_csv(os.path.join(data_folder, 'profiles.csv'), index_col=[0, 1, 2])
+
+    dune_crest_shp = './data/raw/profile_features/dune_crests.shp'
+    dune_toe_shp = './data/raw/profile_features/dune_toes.shp'
+    df_profile_features = parse_profile_features(df_sites, df_profiles, dune_crest_shp, dune_toe_shp)
+    df_profile_features.to_csv('./data/interim/profile_features.csv')