Code cleanup

Author: hovnatan

superannotate/analytics/class_analytics.py

@@ -1,13 +1,13 @@
-from .common import aggregate_annotations_as_df
-
+import json
+import logging
 from pathlib import Path
+
+import pandas as pd
 import plotly.express as px
-from plotly.subplots import make_subplots
 import plotly.graph_objects as go
-import pandas as pd
+from plotly.subplots import make_subplots
 
-import json
-import logging
+from .common import aggregate_annotations_as_df
 
 logger = logging.getLogger("superannotate-python-sdk")
 
@@ -19,7 +19,7 @@ def class_distribution(export_root, project_names, visualize=False):
     :type export_root: Pathlike (str or Path)
     :param project_names: list of project names to aggregate through
     :type project_names: list of str
-    :param visulaize: enables class histogram plot
+    :param visualize: enables class histogram plot
     :type visualize: bool
     :return: DataFrame on class distribution with columns ["className", "count"]
     :rtype: pandas DataFrame
@@ -72,7 +72,7 @@ def attribute_distribution(export_root, project_names, visualize=False):
     :type project_names: list of str
     :param visulaize: enables attribute histogram plot
     :type visualize: bool
-    :return: DataFrame on attribute distribution with columns ["className", "attributeGroupName", "attributeName", "count"] 
+    :return: DataFrame on attribute distribution with columns ["className", "attributeGroupName", "attributeName", "count"]
     :rtype: pandas DataFrame
     """
 

superannotate/analytics/user_analytics.py

@@ -1,13 +1,13 @@
 import pandas as pd
-from tqdm import tqdm
 import plotly.express as px
 
-def image_analytics(annotations_df, visualize = False):
+
+def image_analytics(annotations_df, visualize=False):
     """
     Aggregates image analytics: num instances/annotation time in seconds per image
     :param annotations_df: pandas DataFrame of project annotations
     :type annotations_df: pandas.DataFrame
-    :param visulaize: enables image analytics scatter plot
+    :param visualize: enables image analytics scatter plot
     :type visualize: bool
 
     :return: DataFrame on image analytics with columns ["userEmail", "userRole", "imageName", "annotationTime", "instanceCount"]
@@ -19,16 +19,26 @@ def fix_spent_time(grp: pd.Series) -> pd.Series:
         grp_lost_msk = (grp > 600) | (grp.isna())
         grp.loc[grp_lost_msk] = grp[~grp_lost_msk].median()
         return grp
-    
-    analytics = {"userEmail": [], "userRole": [], "imageName": [], "annotationTime": [], "instanceCount": [] }
-    annot_cols = ["imageName", "instanceId", "createdAt", "creatorEmail", "creatorRole"]
-    annotations_df = annotations_df[annotations_df["creationType"] == "Manual"][annot_cols].drop_duplicates()
+
+    analytics = {
+        "userEmail": [],
+        "userRole": [],
+        "imageName": [],
+        "annotationTime": [],
+        "instanceCount": []
+    }
+    annot_cols = [
+        "imageName", "instanceId", "createdAt", "creatorEmail", "creatorRole"
+    ]
+    annotations_df = annotations_df[annotations_df["creationType"] == "Manual"
+                                   ][annot_cols].drop_duplicates()
 
     for annot, grp in annotations_df.groupby(["creatorEmail", "creatorRole"]):
         grp_sorted = grp.sort_values("createdAt")
         time_spent = grp_sorted.createdAt.diff().shift(-1).dt.total_seconds()
         grp["time_spent"] = fix_spent_time(time_spent)
-        img_time = grp.groupby("imageName", as_index=False)["time_spent"].agg("sum")
+        img_time = grp.groupby("imageName",
+                               as_index=False)["time_spent"].agg("sum")
         img_n_instance = grp.groupby("imageName")["instanceId"].agg("count")
 
         analytics["imageName"] += img_time.imageName.tolist()
@@ -46,8 +56,12 @@ def fix_spent_time(grp: pd.Series) -> pd.Series:
             y="annotationTime",
             color="userEmail",
             facet_col="userRole",
-            custom_data = ["imageName"],
-            labels = {'userEmail': "User Email", "instanceCount": "Number of Instances", "annotationTime": "Annotation time"},
+            custom_data=["imageName"],
+            labels={
+                'userEmail': "User Email",
+                "instanceCount": "Number of Instances",
+                "annotationTime": "Annotation time"
+            },
             color_discrete_sequence=px.colors.qualitative.Dark24,
         )
         fig.for_each_annotation(lambda a: a.update(text=a.text.split("=")[-1]))

tests/analytics/test_class_analytics.py

@@ -1,8 +1,8 @@
-import pytest
 from pathlib import Path
-import superannotate as sa
 
-sa.init(Path.home() / ".superannotate" / "config.json")
+import pytest
+
+import superannotate as sa
 
 test_root = Path().resolve() / 'tests'