added debris by activity

cleanup.py

@@ -277,11 +277,14 @@ def read_col_config(column_config='column_categories.yml'):
         material = 'Mixed'
         required = False
         col_type = 'int'
+        activity = 'Various'
         if col_info is not None:
             if 'sources' in col_info:
                 source_names += col_info['sources']
             if 'material' in col_info:
                 material = col_info['material']
+            if 'activity' in col_info:
+                activity = col_info['activity']
             if 'required' in col_info and isinstance(col_info['required'], bool):
                 required = col_info['required']
             if 'type' in col_info and isinstance(col_info['type'], str):
@@ -291,13 +294,17 @@ def read_col_config(column_config='column_categories.yml'):
             'sources': source_names,
             'type': col_type,
             'required': required,
-            'material': material}
+            'material': material,
+            'activity': activity,
+        }
     # Add 'Other' to config as well
     config['Other'] = {
         'sources': ['Any items not in config'],
         'type': 'int',
         'required': False,
-        'material': 'Mixed'}
+        'material': 'Mixed',
+        'activity': 'Various',
+    }
     return config
 
 

column_categories.yml

@@ -3,71 +3,92 @@ Date:
   type: datetime
   required: True
   material: "NA"
+  activity: 'NA'
 Cleanup Site:
   sources: ['Cleanup Site/Sitio De Limpieza']
   type: str
   required: True
   material: "NA"
+  activity: 'NA'
 Cleaned Size (Sq Miles):
   sources: ['Estimated Size Of Location Cleaned (Sq Miles)',
             'Cleanup Area']
   type: int
   required: False
   material: "NA"
+  activity: 'NA'
 Data Collection:
   sources: ['Data Collection Method']
   type: str
   material: "NA"
+  activity: 'NA'
 Duration (Hrs):
   sources: ['Total Cleanup Duration (Hrs)']
   type: int
   required: True
   material: "NA"
+  activity: 'NA'
 Adult Volunteers:
   sources: ['# Of Volunteers']
   type: int
   required: True
   material: "NA"
+  activity: 'NA'
 Youth Volunteers:
   material: "NA"
+  activity: 'NA'
 Trash (lbs):
   sources: ['Pounds Of Trash Collected', 'Pounds Of Trash']
   type: float
   material: "NA"
+  activity: 'NA'
 Recycling (lbs):
   sources: ['Pounds Of Recycle Collected', 'Pounds Of Recycling']
   type: float
   material: "NA"
+  activity: 'NA'
 County/City:
   sources: ['County/City Where The Event Was Held?', 'County', 'City/County']
   type: str
   material: "NA"
+  activity: 'NA'
 Type Of Cleanup:
   sources: []
   type: 'str'
   material: "NA"
+  activity: 'NA'
 Aluminum Foil:
   sources: []
   material: 'Metal'
+  activity: "Various"
 Appliances:
   sources: ['Appliances (Refrigerators, Washers, Etc.)']
   material: 'Metal'
+  activity: 'Dumping/Disaster'
 Bagged Pet Waste:
   sources: ['Dog Poop Bags']
+  activity: "Recreation"
 Balloons:
   sources: ['Balloons Or Ribbon']
   material: 'Plastic'
+  activity: "Recreation"
 Bandaids:
   sources: ['Bandaids Or Bandages']
+  activity: "Hygiene"
 Batteries:
+  material: 'Metal'
+  activity: 'Dumping/Disaster'
 Beverage Pouches:
   sources: ['Beverages Sachets/Pouches', 'Beverages Sachets']
   material: 'Plastic'
+  activity: "Eating/Drinking"
 Beach Gear:
   sources: ['Toys And Beach Accessories', 'Beach Chairs, Toys Umbrellas', 'Sunglasses']
+  activity: "Recreation"
 Bikes:
   sources: ['Bikes Or Bike Parts']
   material: 'Metal'
+  activity: "Recreation"
 Bottle Caps:
   sources: ['Bottle Caps And Rings',
             'Metal Bottle Caps',
@@ -78,26 +99,35 @@ Bottle Caps:
             'Bottle Caps (Plastic)',
             'Bottle Caps (Metal)']
   material: 'Mixed'
+  activity: "Various"
 Cans:
   sources: ['Beverage Cans',
             'Beer Cans',
             'Soda Cans',
             'Metal Beverage Cans']
   material: 'Metal'
+  activity: "Eating/Drinking"
 Car Parts:
+  activity: 'Dumping/Disaster'
 Cigar Tips:
+  activity: 'Smoking'
 Cigarette Butts:
   material: 'Plastic'
+  activity: 'Smoking'
 Clothes:
   sources: ['Clothes, Cloth', 'Clothes Or Towels']
+  activity: 'Recreation'
 Construction Materials:
   sources: []
+  activity: 'Dumping/Disaster'
 E-Waste:
   sources: ['Vape Items/ E-Smoking Devices',
             'E-Cigarettes']
   material: 'Mixed'
+  activity: 'Smoking'
 Fireworks:
   sources: ['Fireworkds']
+  activity: 'Recreation'
 Fishing Gear:
   sources: ['Fishing Gear (Lures, Nets, Etc.)',
             'Fishing Lines, Nets, Traps, Ropes, Pots',
@@ -111,6 +141,7 @@ Fishing Gear:
             'Fishing Pole',
             'Fishing Line']
   material: 'Mixed'
+  activity: 'Fishing'
 Food Containers:
   sources: ['Food Containers, Cups, Plates, Bowls',
             'Food Containers (Plastic)',
@@ -135,30 +166,38 @@ Food Containers:
             'Plastic Cups, Lids, Plates, Utensils',
             'Styrofoam Cups, Plates And Bowls New']
   material: 'Mixed'
+  activity: 'Eating/Drinking'
 Food Wrappers:
   sources: ['Plastic Food Wrappers',
             'Food Wrappers',
             'Food Wrapper',
             'Plastic Food Wrappers (Ie Chips Or Candy)']
   material: 'Plastic'
+  activity: 'Eating/Drinking'
 Footwear:
   sources: ['Footwear (Shoes/Slippers)', 'Shoes']
+  activity: 'Recreation'
 Glass Bottles:
   sources: ['Beverage Bottles (Glass)']
   material: 'Glass'
+  activity: 'Eating/Drinking'
 Glass Pieces:
   sources: ['Glass Pieces And Chunks', 'Pieces And Chunks']
   material: 'Glass'
+  activity: 'Various'
 Lighters:
   sources: ['Cigarette Lighters',
             'Disposable Lighters',
             'Disposable Cigarette Lighters']
   material: 'Mixed'
+  activity: 'Smoking'
 Nails:
   sources: ['Metal Nails']
   material: 'Metal'
+  activity: 'Dumping/Disaster'
 Paper Pieces:
   material: 'Wood'
+  activity: 'Various'
 Paper/Cardboard:
   sources: ['Cardboard',
             'Paper Cardboard',
@@ -167,6 +206,7 @@ Paper/Cardboard:
             'Paper Newpapers/ Magazines',
             'Newspapers/Magazines']
   material: 'Wood'
+  activity: 'Various'
 Personal Hygiene:
   sources: ['Condoms',
             'Diapers',
@@ -177,6 +217,7 @@ Personal Hygiene:
             'Wipes',
             'Feminine Hygeine Products']
   material: 'Mixed'
+  activity: 'Hygiene'
 Plastic Bags:
   sources: ['Shopping Bags',
             'Other Plastic Bags',
@@ -187,28 +228,33 @@ Plastic Bags:
             'Grocery Bags (Plastic)',
             'Plastic Bags (Trash) New']
   material: 'Plastic'
+  activity: 'Eating/Drinking'
 Plastic Bottles:
   sources: ['Other Plastic Bottles (Oil, Bleach, Etc.)',
             'Plastic Motor Oil Bottles',
             'Other Plastic Bottles',
             'Beverage Bottles (Plastic)']
   material: 'Plastic'
+  activity: 'Various'
 Lids:
   sources: ['Lids (Plastic)', 'Plastic Lids']
   material: 'Plastic'
+  activity: 'Various'
 Packaging:
   sources: ['Foam Packaging',
             'Other Plastic/ Foam Packaging',
             'Other Plastic/Foam Packaging',
             'Other Packaging (Clean Swell)',
             'Styrofoam Peanuts Or Packing Materials']
   material: 'Plastic'
+  activity: 'Various'
 Plastic Pieces:
   sources: ['Polystyrene Pieces',
             'Foam Dock Pieces',
             'Styrofoam Pieces',
             'Foam Pieces']
   material: 'Plastic'
+  activity: 'Various'
 To-Go Items:
   sources: ['Plastic To-Go Items',
             'Plastic Polystyrene Food "To-Go" Containers',
@@ -217,39 +263,50 @@ To-Go Items:
             'Take Out/Away (Plastic',
             'Take Out/Away (Foam)']
   material: 'Plastic'
+  activity: 'Eating/Drinking'
 PPE:
   sources: ['Personal Protective Equipment (Masks, Gloves)',
             'Personal Protective Equipment']
   material: 'Mixed'
+  activity: 'Hygiene'
 Rope:
   sources: ['Rope (Yard Pieces)', 'Rope', 'Rope (1 Yard/Meter = 1 Piece)']
+  activity: 'Various'
 Strapping Bands:
+  activity: 'Various'
 Straws:
   sources: ['Straws/Stirrers',
             'Straws And Stirrers',
             'Plastic Straws Or Stirrers']
   material: 'Plastic'
+  activity: 'Eating/Drinking'
 Syringes:
   sources: ['Syringes/Needles', 'Syringes Or Needles', 'Syringes']
   material: 'Metal'
+  activity: 'Hygiene'
 Tires:
+  activity: 'Dumping/Disaster'
 Tobacco:
   sources: ['Smoking, Tobacco (Not E-Waste Or Butts)',
             'Tobacco Packaging/Wrap',
             'Smoking, Tobacco, Vape Items (Not Butts)',
             'Cigarette Box Or Wrappers',
             'Other Tobacco (Packaging, Lighter, Etc.)']
+  activity: 'Smoking'
 Utensils:
   sources: ['Utensils (Plastic)', 'Forks, Knives, Spoons']
   material: 'Plastic'
+  activity: 'Eating/Drinking'
 Wood Pieces:
   sources: ['Wood Pallets, Pieces And Processed Wood',
             'Wood Pieces',
             'Pallets Or Wood']
   material: 'Wood'
+  activity: 'Dumping/Disaster'
 6-Pack Holders:
   sources: ['Plastic Six-Pack Rings', '6Ppack Holders']
   material: 'Plastic'
+  activity: 'Eating/Drinking'
 
 
 

graphs.py

@@ -236,6 +236,40 @@ def map_graph(df, map_bounds=None, w=None, h=None, single_color=True):
     return fig
 
 
+def activity_graph(df, col_config):
+    col_sum = df.copy()
+    # Drop non-activity columns
+    nonitem_cols = list(col_config.loc[col_config['activity'].isnull()]['name'])
+    # Sum total items
+    col_sum.drop(nonitem_cols, axis=1, inplace=True)
+    col_sum = col_sum.sum(axis=0, numeric_only=True)
+    col_sum = col_sum.sort_values(ascending=False)
+    # Add activity to dataframe
+    col_sum = col_sum.to_frame(name='count')
+    col_sum.insert(0, 'name', col_sum.index)
+    col_sum.reset_index(drop=True, inplace=True)
+    col_sum = pd.merge(col_sum, col_config, how='left', on="name")
+    # Bar plot
+    fig = px.bar(col_sum, x='activity', y='count', color='name', text="name")
+    fig.update_layout(
+        autosize=False,
+        width=1000,
+        height=700,
+        title="Total Number of Items Collected By Activity, 2013-23",
+        yaxis_title='Total Number of Items',
+        xaxis_title='Activity',
+        legend_title='Item Category',
+        xaxis={'categoryorder': 'total descending'},
+    )
+    fig.update_traces(
+        textfont_size=10,
+        textangle=0,
+        textposition="inside",
+        cliponaxis=False,
+    )
+    return fig
+
+
 def make_and_save_graphs(sos_data, data_dir, ext='.png'):
     """
     Manipulate the data frame to extract features, plot graphs, and write
@@ -244,12 +278,12 @@ def make_and_save_graphs(sos_data, data_dir, ext='.png'):
 
     :param pd.DataFrame sos_data: SOS data collected over the years.
     :param str data_dir: Data directory
-    :param st ext: Graph file extention (default: '.png')
+    :param str ext: Graph file extention (default: '.png')
     """
     # Creates subdirectory for graphs
     image_dir = os.path.join(data_dir, "Graphs")
     os.makedirs(image_dir, exist_ok=True)
-    # Read config for columns (created when running cleanup main
+    # Read config for columns (created when running cleanup main)
     col_config = pd.read_csv(os.path.join(data_dir, 'sos_column_info.csv'))
     # find column names that do not correspond to items (material is nan)
     nonitem_cols = list(col_config.loc[col_config['material'].isnull()]['name'])
@@ -261,13 +295,13 @@ def make_and_save_graphs(sos_data, data_dir, ext='.png'):
 
     # Create bar graph for years 2013-23
     # Add Total Volunteers and Total Items to col config
-    col_config.loc[len(col_config.index)] = ['Total Volunteers', ['Adult + 0.5*Youth'], 'float', False, np.NaN]
-    col_config.loc[len(col_config.index)] = ['Total Items', ['Sum of items per event'], 'int', False, np.NaN]
+    col_config.loc[len(col_config.index)] = ['Total Volunteers', ['Adult + 0.5*Youth'], 'float', False, np.NaN, np.NaN]
+    col_config.loc[len(col_config.index)] = ['Total Items', ['Sum of items per event'], 'int', False, np.NaN, np.NaN]
     # ...and to dataframe
-    sos_data['Total Volunteers'] = sos_data['Adult Volunteers'].fillna(0) + 0.5 * sos_data['Youth Volunteers'].fillna(0)
     items = sos_data.copy()
     items.drop(nonitem_cols, axis=1, inplace=True)
     sos_data['Total Items'] = items.sum(axis=1, numeric_only=True)
+    sos_data['Total Volunteers'] = sos_data['Adult Volunteers'].fillna(0) + 0.5 * sos_data['Youth Volunteers'].fillna(0)
     # Group by year
     annual_data = cleanup.group_by_year(sos_data, col_config)
     # Sort items by sum in descending order so it's easier to decipher variables
@@ -411,6 +445,9 @@ def make_and_save_graphs(sos_data, data_dir, ext='.png'):
     )
     fig.write_image(os.path.join(image_dir, "Line_graph_smoking_per_volunteers_2013-23" + ext))
 
+    # Debris by activity
+    fig = activity_graph(sos_data, col_config)
+    fig.write_image(os.path.join(image_dir, "Debris_by_activity_2013-23" + ext))
 
 if __name__ == '__main__':
     args = cleanup.parse_args()