extend ocr evaluation results

3 files changed, 38 insertions, 34 deletions

diff --git a/bjoern/videoanalyse/post_processing.py b/bjoern/videoanalyse/post_processing.py
index 445b72f..c295dc6 100644
--- a/bjoern/videoanalyse/post_processing.py
+++ b/bjoern/videoanalyse/post_processing.py
@@ -20,6 +20,7 @@ all_vp = [x for x in data_path.iterdir() if x.is_dir()]
 
 vp_results = []
 tab_results = []
+log_tab_results = []
 for vp_path in all_vp:
     log = LogParser.extract_activities(LogParser.get_log_data(vp_path))
     log = LogParser.generate_log(log)
@@ -45,11 +46,15 @@ for vp_path in all_vp:
 
     df = pd.read_csv(f"{vp_path}/metrics_grps.csv")
 
-    tab_df = tab_switch.tab_switches_per_type(df)
+    tab_df = tab_switch.tab_switches_per_type(df, "group_index")
     tab_results.append(tab_df)
     tab_df.to_csv(f"{vp_path}/tabswitches.csv")
 
+    log_tab_df = tab_switch.tab_switches_per_type(df, "log_url")
+    log_tab_results.append(log_tab_df)
+    log_tab_df.to_csv(f"{vp_path}/log_tabswitches.csv")
+
     vp_results.append(df)
 
-evals = utils.evaluate_results(tab_results)
+evals = utils.evaluate_results(tab_results, log_tab_results)
 evals.to_csv(f"{data_path}/evaluation.csv")
diff --git a/bjoern/videoanalyse/tab_switch.py b/bjoern/videoanalyse/tab_switch.py
index 2efa647..a0bb5de 100644
--- a/bjoern/videoanalyse/tab_switch.py
+++ b/bjoern/videoanalyse/tab_switch.py
@@ -3,15 +3,7 @@
 import pandas as pd
 
 
-def tab_switches_per_type(df):
-    # url_types = ["url", "log_url", "longest", "most_frequent"]
-    # dist_types = [
-    #     "levenshtein-distance",
-    #     "levenshtein-distance",
-    #     "longest-distance",
-    #     "most_frequent-distance",
-    # ]
-
+def tab_switches_per_type(df, key_column):
     result = {
         "vp_code": [],
         "log_url": [],
@@ -26,7 +18,7 @@ def tab_switches_per_type(df):
     count = -1
     for row in df.iterrows():
         row = row[1]
-        if row["group_index"] != last_group:
+        if row[key_column] != last_group:
             result["vp_code"].append(row["vp_code"])
             result["group"].append(row["group_index"])
             result["log_url"].append(row["log_url"])
@@ -35,7 +27,7 @@ def tab_switches_per_type(df):
             result["most_frequent_url"].append(row["most_frequent"])
             result["most_frequent-distance"].append(row["most_frequent-distance"])
 
-            last_group = row["group_index"]
+            last_group = row[key_column]
             if count == -1:
                 count = 1
                 continue
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