add tab switching results

1 files changed, 48 insertions, 0 deletions

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