extend ocr evaluation results

1 files changed, 28 insertions, 21 deletions

diff --git a/bjoern/videoanalyse/utils.py b/bjoern/videoanalyse/utils.py
index df00482..f9b2ca0 100644
--- a/bjoern/videoanalyse/utils.py
+++ b/bjoern/videoanalyse/utils.py
@@ -42,13 +42,15 @@ def combine_ocr_logs(video_path, ocr_path, log_path):
     # analysis.to_csv(vp_path / "merged.csv", quoting=csv.QUOTE_NONNUMERIC)
     return analysis
 
+
 def levendist_normalized(s1, s2, log_url):
     return levendist(s1, s2) / len(str(log_url))
 
 
 def calc_levenshtein_distance(df):
     df["levenshtein-distance"] = df.apply(
-        lambda row: levendist(str(row.url), str(row.log_url)) / len(str(row.log_url)), axis=1
+        lambda row: levendist(str(row.url), str(row.log_url)) / len(str(row.log_url)),
+        axis=1,
     )
     return df
 
@@ -124,44 +126,49 @@ def write_grouped_metrics(df, url_groups, data_path):
                     row.append(levendist_normalized(log_url, longest_in_grp, log_url))
                     most_frequent_in_grp = max(set(grp), key=grp.count)
                     row.append(str(most_frequent_in_grp))
-                    row.append(levendist_normalized(log_url, most_frequent_in_grp, log_url))
+                    row.append(
+                        levendist_normalized(log_url, most_frequent_in_grp, log_url)
+                    )
             csv_writer.writerow(row)
 
 
-def evaluate_results(vp_results):
-    vp_code = [df["vp_code"].values[0] for df in vp_results]
-    # mean_lev = [
-    #     sum(df["levenshtein-distance"].values) / len(df["levenshtein-distance"])
-    #     for df in vp_results
-    # ]
+def evaluate_results(tab_results, log_tab_results):
+    vp_code = [df["vp_code"].values[0] for df in tab_results]
+
     mean_long = []
     mean_freq = []
-    for df in vp_results:
-        groups = set(df["group"].values)
+    count_groups = []
+    count_log_urls = []
+    count_grp_diff = []
+    grp_tabswitches = []
+    tabswitches_diff = []
+    for tab_df, log_tab_df in zip(tab_results, log_tab_results):
+        groups = set(tab_df["group"].values)
         group_long = 0
         group_freq = 0
+        count_groups.append(len(groups))
+        count_log_urls.append(len(set(tab_df["log_url"].values)))
+        count_grp_diff.append(len(groups) - len(set(tab_df["log_url"].values)))
+        grp_tabswitches.append(len(tab_df["group"].values))
+        tabswitches_diff = len(tab_df["group"].values) - len(log_tab_df["group"].values)
         for group in groups:
-            group_df = df.loc[df['group'] == group]
+            group_df = tab_df.loc[tab_df["group"] == group]
             group_long += group_df["longest-distance"].values[0]
             group_freq += group_df["most_frequent-distance"].values[0]
         mean_long.append(group_long / len(groups))
         mean_freq.append(group_freq / len(groups))
 
-    # mean_long = [
-    #     sum(df["longest-distance"].values) / len(df["longest-distance"])
-    #     for df in vp_results
-    # ]
-    # mean_freq = [
-    #     sum(df["most_frequent-distance"].values) / len(df["most_frequent-distance"])
-    #     for df in vp_results
-    # ]
-
     metrics = {
         "vp_code": vp_code,
-        # "mean_lev": mean_lev,
         "mean_long": mean_long,
         "mean_freq": mean_freq,
+        "count_groups": count_groups,
+        # "count_log_urls": count_log_urls,
+        "count_grp_diff": count_grp_diff,
+        "grp_tabswitches": grp_tabswitches,
+        "tabswitches_diff": tabswitches_diff,
     }
+
     evals = pd.DataFrame(metrics)
 
     return evals