add tab switching results

2 files changed, 55 insertions, 2 deletions

diff --git a/bjoern/videoanalyse/post_processing.py b/bjoern/videoanalyse/post_processing.py
index b5e3c65..445b72f 100644
--- a/bjoern/videoanalyse/post_processing.py
+++ b/bjoern/videoanalyse/post_processing.py
@@ -8,6 +8,7 @@ import pandas as pd
 
 import LogParser
 import utils
+import tab_switch
 
 argparser = argparse.ArgumentParser(description="OCR-Logfile evaluation")
 argparser.add_argument("vp_dir", help="Directory with all VPs")
@@ -18,6 +19,7 @@ data_path = Path(args.vp_dir)
 all_vp = [x for x in data_path.iterdir() if x.is_dir()]
 
 vp_results = []
+tab_results = []
 for vp_path in all_vp:
     log = LogParser.extract_activities(LogParser.get_log_data(vp_path))
     log = LogParser.generate_log(log)
@@ -43,8 +45,11 @@ 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_results.append(tab_df)
+    tab_df.to_csv(f"{vp_path}/tabswitches.csv")
+
     vp_results.append(df)
 
-evals = utils.evaluate_results(vp_results)
-pprint(evals)
+evals = utils.evaluate_results(tab_results)
 evals.to_csv(f"{data_path}/evaluation.csv")
diff --git a/bjoern/videoanalyse/tab_switch.py b/bjoern/videoanalyse/tab_switch.py
new file mode 100644
index 0000000..2efa647
--- /dev/null
+++ b/bjoern/videoanalyse/tab_switch.py
@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+
+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",
+    # ]
+
+    result = {
+        "vp_code": [],
+        "log_url": [],
+        "count": [],
+        "group": [],
+        "longest_url": [],
+        "longest-distance": [],
+        "most_frequent_url": [],
+        "most_frequent-distance": [],
+    }
+    last_group = -1
+    count = -1
+    for row in df.iterrows():
+        row = row[1]
+        if row["group_index"] != last_group:
+            result["vp_code"].append(row["vp_code"])
+            result["group"].append(row["group_index"])
+            result["log_url"].append(row["log_url"])
+            result["longest_url"].append(row["longest"])
+            result["longest-distance"].append(row["longest-distance"])
+            result["most_frequent_url"].append(row["most_frequent"])
+            result["most_frequent-distance"].append(row["most_frequent-distance"])
+
+            last_group = row["group_index"]
+            if count == -1:
+                count = 1
+                continue
+            result["count"].append(count)
+            count = 1
+        else:
+            count += 1
+    result["count"].append(count)
+    result_df = pd.DataFrame(result)
+    return result_df