From 77548a6de85222c68acc690c989a9d217f8cdaf3 Mon Sep 17 00:00:00 2001
From: Joscha <joscha@plugh.de>
Date: Sat, 1 Mar 2025 03:50:31 +0100
Subject: [PATCH] Add activity graph script

---
 activity_graph.py | 95 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)
 create mode 100644 activity_graph.py

diff --git a/activity_graph.py b/activity_graph.py
new file mode 100644
index 0000000..93518fd
--- /dev/null
+++ b/activity_graph.py
@@ -0,0 +1,95 @@
+import argparse
+import datetime
+import json
+from collections import Counter
+from pathlib import Path
+
+import matplotlib.dates as mdates
+import matplotlib.pyplot as plt
+import pandas as pd
+
+
+class Data:
+    def __init__(self):
+        self.by_day = Counter()
+
+    def add_msg(self, msg):
+        dt = datetime.datetime.fromtimestamp(msg["time"], tz=datetime.UTC)
+        self.by_day[dt.date()] += 1
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("json_logs", type=Path, nargs="+")
+    args = parser.parse_args()
+
+    data = Data()
+
+    for path in args.json_logs:
+        print(f"Reading {path}")
+        n = 0
+        with open(path) as f:
+            for line in f:
+                data.add_msg(json.loads(line))
+                n += 1
+                if n % 100000 == 0:
+                    print(f"{n:10}")
+        print(f"{n:10}")
+
+    first_day = min(data.by_day.keys())
+    last_day = max(data.by_day.keys())
+    print(f"Got logs from {first_day} to {last_day}")
+
+    # The following code was generated by ChatGPT and adjusted by me
+
+    # Extract sorted dates and counts
+    dates = sorted(data.by_day.keys())
+    counts = [data.by_day[date] for date in dates]
+
+    # Convert to DataFrame for moving average calculation
+    df = pd.DataFrame({"date": dates, "count": counts})
+    df.set_index("date", inplace=True)
+    df = df.asfreq("D", fill_value=0)  # Fill missing dates with 0
+    df["30_day_avg"] = df["count"].rolling(window="30D", center=True).mean()
+
+    # Create the plot
+    fig, ax = plt.subplots(figsize=(10, 5))
+    ax.plot(
+        df.index,
+        df["count"],
+        linestyle="-",
+        linewidth=0.5,
+        color="#348ceb",
+        label="Messages",
+    )
+    ax.plot(
+        df.index,
+        df["30_day_avg"],
+        linestyle="-",
+        linewidth=0.5,
+        color="#a80303",
+        label="30-day moving average",
+    )
+
+    # Format x-axis for better readability
+    ax.xaxis.set_major_locator(mdates.YearLocator())  # Major ticks per year
+    ax.xaxis.set_minor_locator(mdates.MonthLocator())  # Minor ticks per month
+    ax.xaxis.set_major_formatter(mdates.DateFormatter("%Y"))  # Year labels
+    ax.set_xlabel("Time")
+    ax.set_ylabel("Messages")
+    ax.set_ylim(0)  # Start y-axis at 0
+    ax.set_title("Activity Graph™")
+    ax.legend()
+    ax.grid(True, which="both", linestyle="--", linewidth=0.5)
+
+    # Rotate x-axis labels for clarity
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+
+    # Save the plot to a PNG file
+    plt.savefig("activity_graph.png", dpi=300)
+    plt.close()
+
+
+if __name__ == "__main__":
+    main()