.

cw2.py

@@ -44,6 +44,8 @@ def get_views_by_continent(data, doc_uuid):
 def get_visitor_useragents(data):
     fig = plt.figure(figsize=(10, 6))
     data['visitor_useragent'].value_counts().plot(kind='bar')
+    plt.xlabel("Visitor User Agents")
+    plt.ylabel("Frequency")
     return fig
 
 
@@ -51,6 +53,8 @@ def get_visitor_browsers(data):
     fig = plt.figure(figsize=(10, 6))
     data['visitor_browser'] = data['visitor_useragent'].str.split('/').str[0]
     data['visitor_browser'].value_counts().plot(kind='bar')
+    plt.xlabel("Visitor Browsers")
+    plt.ylabel("Frequency")
     return fig
 
 
@@ -60,33 +64,14 @@ def get_avid_readers(data):
 
 def plot_avid_readers(data):
     fig = plt.figure(figsize=(11, 7))
+    plt.tight_layout()
     get_avid_readers(data).sort_values(ascending=True).plot(kind='barh')
+    plt.xlabel("Time in minutes")
+    plt.ylabel("Visitor UUID")
+    plt.tight_layout()
     return fig
 
 
-# def get_doc_visitors(doc_uuid):
-#     return data_tiny[data_tiny['subject_doc_id'] == doc_uuid]['visitor_uuid'].unique()
-#
-#
-# def get_visitor_docs(visitor_uuid):
-#     return data_tiny[data_tiny['visitor_uuid'] == visitor_uuid]['subject_doc_id'].dropna().unique()
-#
-#
-# def get_also_likes_doc(doc_uuid, visitor_uuid, ascending):
-#     visitor_uuids = get_doc_visitors(doc_uuid)
-#     doc_uuids = sum([list(get_visitor_docs(reader)) for reader in visitor_uuids], [])
-#     return pd.Series(doc_uuids).value_counts(ascending=ascending)
-#
-#
-# def also_like(doc_uuid, visitor_uuid, ascending):
-#     visitor_uuids = get_doc_visitors(doc_uuid)
-#     y = []
-#     for reader in visitor_uuids:
-#         for doc in get_visitor_docs(reader):
-#             if doc != doc_uuid and doc not in get_visitor_docs(visitor_uuid).tolist():
-#                 y.append([reader, doc])
-#     return pd.DataFrame(y)
-
 # Req 5a
 def get_doc_visitors(data, doc_uuid):
     readers = data[data['env_type'] == "reader"]
@@ -140,7 +125,7 @@ def also_like_graph(data, doc_uuid, visitor_uuid, ascending):
         dot.edge(str(row[0]), str(row[1]))
 
     # print(dot.source)
-    
+
     dot.render('output.dot').replace('\\', '/')
 
     (graph,) = pydot.graph_from_dot_file('output.dot')