piholelongtermstats 0.2.0__tar.gz → 0.2.2__tar.gz

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: piholelongtermstats
-Version: 0.2.0
+Version: 0.2.2
 Summary: A dashboard to explore long-term DNS query data from Pi-hole FTL database files.
 Author-email: Davis Thomas Daniel <davisthomasdaniel@gmail.com>
 Maintainer-email: Davis Thomas Daniel <davisthomasdaniel@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/davistdaniel/PiHoleLongTermStats
-Project-URL: Documentation, https://readthedocs.org
+Project-URL: Documentation, https://github.com/davistdaniel/PiHoleLongTermStats
 Project-URL: Repository, https://github.com/davistdaniel/PiHoleLongTermStats.git
 Project-URL: Bug Tracker, https://github.com/davistdaniel/PiHoleLongTermStats/issues
 Keywords: dashboard,pihole,visualization,plotly,dash
@@ -26,7 +26,7 @@ Requires-Dist: twine==6.2.0; extra == "develop"
 Requires-Dist: pytest-cov==7.0.0; extra == "develop"
 Dynamic: license-file
 
-# Pi Hole Long Term Statistics v.0.2.0
+# Pi Hole Long Term Statistics v.0.2.2
 
 A dashboard built with **Dash** and **Plotly** to explore long-term DNS query data from **Pi-hole v.6** FTL database files. Visualize allowed vs blocked domains, top clients, and query trends over time. I originally made this for my own use, but if you find it useful, a ⭐ would be awesome!
 

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/README.md

@@ -1,4 +1,4 @@
-# Pi Hole Long Term Statistics v.0.2.0
+# Pi Hole Long Term Statistics v.0.2.2
 
 A dashboard built with **Dash** and **Plotly** to explore long-term DNS query data from **Pi-hole v.6** FTL database files. Visualize allowed vs blocked domains, top clients, and query trends over time. I originally made this for my own use, but if you find it useful, a ⭐ would be awesome!
 

piholelongtermstats-0.2.2/piholelongtermstats/__init__.py

@@ -0,0 +1,3 @@
+## Author :  Davis T. Daniel
+## PiHoleLongTermStats v.0.2.2
+## License :  MIT

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/piholelongtermstats/app.py

@@ -1,11 +1,10 @@
 ## Author :  Davis T. Daniel
-## PiHoleLongTermStats v.0.2.0
+## PiHoleLongTermStats v.0.2.2
 ## License :  MIT
 
 import os
 import gc
 import argparse
-import itertools
 import logging
 import psutil
 import plotly.express as px
@@ -20,9 +19,13 @@ from piholelongtermstats.process import (
     prepare_hourly_aggregated_data,
 )
 from piholelongtermstats.stats import compute_stats
-from piholelongtermstats.plot import generate_plot_data
+from piholelongtermstats.plot import (
+    generate_plot_data,
+    generate_client_activity_over_time,
+    generate_queries_over_time,
+)
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 
 # logging setup
 logging.basicConfig(
@@ -193,6 +196,15 @@ def serve_layout(
     del df, hourly_data
     gc.collect()
 
+    # generate initial plots
+
+    initial_filtered_fig = generate_queries_over_time(
+        callback_data=callback_data, client=None
+    )
+    initial_activity_fig = generate_client_activity_over_time(
+        callback_data=callback_data, n_clients=args.n_clients, client=None
+    )
+
     layout = html.Div(
         [
             html.Div(
@@ -688,7 +700,7 @@ def serve_layout(
             html.Div(
                 [
                     html.H2("Queries over time"),
-                    html.H5("Aggregated hourly"),
+                    html.H5("Queries from all clients. The data is aggregated hourly."),
                     dcc.Dropdown(
                         options=[
                             {"label": c, "value": c} for c in plot_data["client_list"]
@@ -696,10 +708,12 @@ def serve_layout(
                         id="client-filter",
                         placeholder="Select a Client",
                     ),
-                    dcc.Graph(id="filtered-view"),
+                    dcc.Graph(id="filtered-view", figure=initial_filtered_fig),
                     html.H2("Client Activity Over Time"),
-                    html.H5("Aggregated hourly"),
-                    dcc.Graph(id="client-activity-view"),
+                    html.H5(
+                        "Client acitivity for all clients. The data is aggregated hourly."
+                    ),
+                    dcc.Graph(id="client-activity-view", figure=initial_activity_fig),
                 ],
                 className="cardplot",
             ),
@@ -707,6 +721,7 @@ def serve_layout(
             html.Div(
                 [
                     html.H2("Top Blocked Domains"),
+                    html.H5(f"Top {args.n_domains} blocked domains."),
                     dcc.Graph(
                         id="top-blocked-domains",
                         figure=px.bar(
@@ -735,6 +750,7 @@ def serve_layout(
             html.Div(
                 [
                     html.H2("Top Allowed Domains"),
+                    html.H5(f"Top {args.n_domains} allowed domains."),
                     dcc.Graph(
                         id="top-allowed-domains",
                         figure=px.bar(
@@ -764,6 +780,7 @@ def serve_layout(
             html.Div(
                 [
                     html.H2("Top Client Activity"),
+                    html.H5(f"Top {args.n_clients} clients based on total queries."),
                     dcc.Graph(
                         id="top-clients",
                         figure=px.bar(
@@ -777,7 +794,6 @@ def serve_layout(
                             },
                             color="status_type",
                             barmode="stack",
-                            title="Top Clients by Query Type",
                             color_discrete_map={
                                 "Allowed": "#10b981",
                                 "Blocked": "#ef4444",
@@ -926,6 +942,7 @@ def serve_layout(
                     html.Div(
                         [
                             html.H2("Average Reply Time"),
+                            html.H5("Daily average reply time in ms."),
                             dcc.Graph(
                                 id="avg-reply-time",
                                 figure=px.line(
@@ -1025,19 +1042,18 @@ app.layout = html.Div(
 del initial_layout
 gc.collect()
 
+
 @app.callback(
     Output("page-container", "children"),
     Input("reload-button", "n_clicks"),
     State("date-picker-range", "start_date"),
     State("date-picker-range", "end_date"),
-    prevent_initial_call=False,
+    prevent_initial_call=True,
 )
 def reload_page(n_clicks, start_date, end_date):
     global PHLTS_CALLBACK_DATA
 
-    logging.info(
-        f"Reload button clicked. Selected date range: {start_date, end_date}"
-    )
+    logging.info(f"Reload button clicked. Selected date range: {start_date, end_date}")
 
     chunksize_list, latest_ts_list, oldest_ts_list = (
         [],
@@ -1075,163 +1091,43 @@ def reload_page(n_clicks, start_date, end_date):
 
     return layout.children
 
+
 @app.callback(
     Output("filtered-view", "figure"),
     Input("client-filter", "value"),
     Input("reload-button", "n_clicks"),
+    prevent_initial_call=True,
 )
 def update_filtered_view(client, n_clicks):
     logging.info("Updating Queries over time plot...")
     global PHLTS_CALLBACK_DATA
 
-    dff_grouped = PHLTS_CALLBACK_DATA["hourly_agg"]
-
-    if client:
-        logging.info(f"Selected client : {client}")
-        dff_grouped = dff_grouped[dff_grouped["client"] == client]
-        title_text = f"DNS Queries Over Time for {client}"
-    else:
-        dff_grouped = (
-            dff_grouped.groupby(["timestamp", "status_type"])["count"]
-            .sum()
-            .reset_index()
-        )
-        title_text = "DNS Queries Over Time for All Clients"
-
-    # Fill missing data with 0
-    all_times = pd.date_range(
-        dff_grouped["timestamp"].min(), dff_grouped["timestamp"].max(), freq="h"
-    )
-    status_types = ["Other", "Allowed", "Blocked"]
-    full_index = pd.MultiIndex.from_product(
-        [all_times, status_types], names=["timestamp", "status_type"]
-    )
-    dff_grouped = (
-        dff_grouped.set_index(["timestamp", "status_type"])
-        .reindex(full_index, fill_value=0)
-        .reset_index()
-    )
-    dff_grouped["status_type"] = pd.Categorical(
-        dff_grouped["status_type"], categories=status_types, ordered=True
-    )
-    dff_grouped = dff_grouped.sort_values("status_type")
-
-    fig = px.area(
-        dff_grouped,
-        x="timestamp",
-        y="count",
-        color="status_type",
-        line_group="status_type",
-        title=title_text,
-        color_discrete_map={
-            "Allowed": "#10b981",
-            "Blocked": "#ef4444",
-            "Other": "#b99529",
-        },
-        template="plotly_white",
-        labels={
-            "timestamp": "Date",
-            "count": "Count",
-            "status_type": "Query Status",
-        },
-    )
-
-    fig.update_traces(
-        mode="lines",
-        line_shape="spline",
-        line=dict(width=0.5),
-        stackgroup="one",
-    )
-
-    fig.update_layout(
-        legend=dict(orientation="h", yanchor="top", y=-0.4, xanchor="center", x=0.5)
-    )
-
-    del dff_grouped
-    gc.collect()
+    fig = generate_queries_over_time(callback_data=PHLTS_CALLBACK_DATA, client=client)
 
     return fig
 
+
 @app.callback(
     Output("client-activity-view", "figure"),
     Input("client-filter", "value"),
     Input("reload-button", "n_clicks"),
+    prevent_initial_call=True,
 )
 def update_client_activity(client, n_clicks):
     logging.info("Updating Client activity over time plot...")
     global PHLTS_CALLBACK_DATA
 
-    dff_grouped = PHLTS_CALLBACK_DATA["hourly_agg"]
-    top_clients = PHLTS_CALLBACK_DATA["top_clients"]
-
-    if client:
-        logging.info(f"Selected client : {client}")
-        dff_grouped = dff_grouped[dff_grouped["client"] == client]
-        dff_grouped = (
-            dff_grouped.groupby(["timestamp", "client"])["count"]
-            .sum()
-            .reset_index()
-        )
-        title_text = f"Activity for {client}"
-        clients_to_show = [client]
-    else:
-        dff_grouped = dff_grouped[dff_grouped["client"].isin(top_clients)]
-        dff_grouped = (
-            dff_grouped.groupby(["timestamp", "client"])["count"]
-            .sum()
-            .reset_index()
-        )
-        title_text = f"Activity for top {args.n_clients} clients"
-        clients_to_show = top_clients
-
-    all_times = pd.date_range(
-        dff_grouped["timestamp"].min(), dff_grouped["timestamp"].max(), freq="h"
+    fig = generate_client_activity_over_time(
+        callback_data=PHLTS_CALLBACK_DATA, n_clients=args.n_clients, client=client
     )
-    full_index = pd.MultiIndex.from_product(
-        [all_times, clients_to_show], names=["timestamp", "client"]
-    )
-    pivot_df = (
-        dff_grouped.set_index(["timestamp", "client"])
-        .reindex(full_index, fill_value=0)
-        .reset_index()
-    )
-
-    default_colors = px.colors.qualitative.Plotly
-    client_color_map = dict(zip(top_clients, itertools.cycle(default_colors)))
-
-    fig = px.area(
-        pivot_df,
-        x="timestamp",
-        y="count",
-        color="client",
-        line_group="client",
-        title=title_text,
-        color_discrete_map=client_color_map,
-        template="plotly_white",
-        labels={"timestamp": "Date", "count": "Count", "client": "Client IP"},
-    )
-
-    fig.update_traces(
-        mode="lines",
-        line_shape="spline",
-        line=dict(width=0.2),
-        stackgroup="one",
-        connectgaps=False,
-    )
-
-    fig.update_layout(
-        legend=dict(orientation="h", yanchor="top", y=-0.4, xanchor="center", x=0.5)
-    )
-
-    del dff_grouped, pivot_df
-    gc.collect()
 
     return fig
 
 
-
 def run():
     app.run(host="0.0.0.0", port=args.port, debug=False)
+
+
 # serve
 if __name__ == "__main__":
     run()

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/piholelongtermstats/db.py

@@ -1,5 +1,5 @@
 ## Author :  Davis T. Daniel
-## PiHoleLongTermStats v.0.2.0
+## PiHoleLongTermStats v.0.2.2
 ## License :  MIT
 
 import sqlite3

piholelongtermstats-0.2.2/piholelongtermstats/plot.py

@@ -0,0 +1,327 @@
+## Author :  Davis T. Daniel
+## PiHoleLongTermStats v.0.2.2
+## License :  MIT
+
+import logging
+import pandas as pd
+import gc
+import plotly.express as px
+import itertools
+
+
+def generate_plot_data(df, n_clients, n_domains):
+    """Generate plot data"""
+
+    logging.info("Generating plot data...")
+
+    def shorten(s):
+        return s if len(s) <= 45 else f"{s[:20]}...{s[-20:]}"
+
+    top_clients = df["client"].value_counts().nlargest(n_clients).index
+    top_clients_stacked = (
+        df[df["client"].isin(top_clients)]
+        .groupby(["client", "status_type"])
+        .size()
+        .reset_index(name="count")
+    )
+    top_clients_stacked["client"] = pd.Categorical(
+        top_clients_stacked["client"],
+        categories=top_clients_stacked.groupby("client")["count"]
+        .sum()
+        .sort_values(ascending=False)
+        .index,
+        ordered=True,
+    )
+    top_clients_stacked = top_clients_stacked.sort_values(
+        ["client", "count"], ascending=[True, False]
+    )
+    logging.info("Generated plot data for top clients.")
+
+    # plot data for allowed and blocked domains
+    tmp_blocked = df[df["status_type"] == "Blocked"].copy()
+    tmp_blocked["domain"] = tmp_blocked["domain"].apply(shorten)
+
+    blocked_df = (
+        tmp_blocked["domain"]
+        .value_counts()
+        .nlargest(n_domains)
+        .reset_index()
+        .rename(columns={"index": "Count", "domain": "Domain"})
+    )
+
+    tmp_allowed = df[df["status_type"] == "Allowed"].copy()
+    tmp_allowed["domain"] = tmp_allowed["domain"].apply(shorten)
+
+    allowed_df = (
+        tmp_allowed["domain"]
+        .value_counts()
+        .nlargest(n_domains)
+        .reset_index()
+        .rename(columns={"index": "Count", "domain": "Domain"})
+    )
+
+    logging.info("Generated plot data for allowed and blocked domains.")
+
+    # plot data for reply time over days
+    reply_time_df = (
+        df.groupby("date")["reply_time"]
+        .mean()
+        .mul(1000)
+        .reset_index(name="reply_time_ms")
+    )
+
+    logging.info("Generated plot data for reply time plot")
+    client_list = df["client"].unique().tolist()
+
+    # plot data for doman-client scatter. take minimum from n_domains or n_clients
+    top_clients = df["client"].value_counts().nlargest(min(n_domains, n_clients)).index
+    top_domains = df["domain"].value_counts().nlargest(min(n_domains, n_clients)).index
+
+    df_top = df.loc[
+        df["client"].isin(top_clients) & df["domain"].isin(top_domains)
+    ].copy()
+    df_top.loc[:, "domain"] = df_top["domain"].apply(shorten)
+
+    client_domain_scatter_df = (
+        df_top.groupby(["client", "domain", "status_type"])
+        .size()
+        .reset_index(name="count")
+        .sort_values(by="count")
+    )
+
+    # heatmap
+    order = [
+        "Monday",
+        "Tuesday",
+        "Wednesday",
+        "Thursday",
+        "Friday",
+        "Saturday",
+        "Sunday",
+    ]
+
+    day_hour_heatmap = (
+        df.groupby(["day_name", "hour"])
+        .size()
+        .reset_index(name="count")
+        .pivot(index="day_name", columns="hour", values="count")
+        .fillna(0)
+        .reindex(order)
+    )
+
+    blocked_day_hour_heatmap = (
+        tmp_blocked.groupby(["day_name", "hour"])
+        .size()
+        .reset_index(name="count")
+        .pivot(index="day_name", columns="hour", values="count")
+        .fillna(0)
+        .reindex(order)
+    )
+
+    allowed_day_hour_heatmap = (
+        tmp_allowed.groupby(["day_name", "hour"])
+        .size()
+        .reset_index(name="count")
+        .pivot(index="day_name", columns="hour", values="count")
+        .fillna(0)
+        .reindex(order)
+    )
+
+    del df_top, top_clients, top_domains, tmp_allowed, tmp_blocked
+    gc.collect()
+
+    logging.info("Plot data generation complete")
+
+    return {
+        "top_clients_stacked": top_clients_stacked,
+        "blocked_df": blocked_df,
+        "allowed_df": allowed_df,
+        "reply_time_df": reply_time_df,
+        "client_list": client_list,
+        "data_span_days": (df["timestamp"].max() - df["timestamp"].min()).days,
+        "client_domain_scatter_df": client_domain_scatter_df,
+        "day_hour_heatmap": day_hour_heatmap,
+        "blocked_day_hour_heatmap": blocked_day_hour_heatmap,
+        "allowed_day_hour_heatmap": allowed_day_hour_heatmap,
+    }
+
+
+def generate_queries_over_time(callback_data, client=None):
+    dff_grouped = callback_data["hourly_agg"]
+
+    if client is not None:
+        logging.info(f"Selected client : {client}")
+        dff_grouped = dff_grouped[dff_grouped["client"] == client]
+        title_text = f"DNS Queries Over Time for {client}"
+    else:
+        dff_grouped = (
+            dff_grouped.groupby(["timestamp", "status_type"])["count"]
+            .sum()
+            .reset_index()
+        )
+        title_text = "DNS Queries Over Time for All Clients"
+
+    if dff_grouped.empty:
+        fig = px.area(
+            title=f"No activity available for {client}"
+            if client
+            else "No activity available",
+            template="plotly_white",
+        )
+        fig.update_layout(
+            xaxis_title="Date",
+            yaxis_title="Count",
+            annotations=[
+                dict(
+                    text="No data to display",
+                    x=0.5,
+                    y=0.5,
+                    xref="paper",
+                    yref="paper",
+                    showarrow=False,
+                )
+            ],
+        )
+        return fig
+
+    # Fill missing data with 0
+    all_times = pd.date_range(
+        dff_grouped["timestamp"].min(), dff_grouped["timestamp"].max(), freq="h"
+    )
+    status_types = ["Other", "Allowed", "Blocked"]
+    full_index = pd.MultiIndex.from_product(
+        [all_times, status_types], names=["timestamp", "status_type"]
+    )
+    dff_grouped = (
+        dff_grouped.set_index(["timestamp", "status_type"])
+        .reindex(full_index, fill_value=0)
+        .reset_index()
+    )
+    dff_grouped["status_type"] = pd.Categorical(
+        dff_grouped["status_type"], categories=status_types, ordered=True
+    )
+    dff_grouped = dff_grouped.sort_values("status_type")
+
+    fig = px.area(
+        dff_grouped,
+        x="timestamp",
+        y="count",
+        color="status_type",
+        line_group="status_type",
+        title=title_text,
+        color_discrete_map={
+            "Allowed": "#10b981",
+            "Blocked": "#ef4444",
+            "Other": "#b99529",
+        },
+        template="plotly_white",
+        labels={
+            "timestamp": "Date",
+            "count": "Count",
+            "status_type": "Query Status",
+        },
+    )
+
+    fig.update_traces(
+        mode="lines",
+        line_shape="spline",
+        line=dict(width=0.5),
+        stackgroup="one",
+    )
+
+    fig.update_layout(
+        legend=dict(orientation="h", yanchor="top", y=-0.4, xanchor="center", x=0.5)
+    )
+
+    del dff_grouped
+    gc.collect()
+
+    return fig
+
+
+def generate_client_activity_over_time(callback_data, n_clients, client=None):
+    dff_grouped = callback_data["hourly_agg"]
+    top_clients = callback_data["top_clients"]
+
+    if client is not None:
+        logging.info(f"Selected client : {client}")
+        dff_grouped = dff_grouped[dff_grouped["client"] == client]
+        dff_grouped = (
+            dff_grouped.groupby(["timestamp", "client"])["count"].sum().reset_index()
+        )
+        title_text = f"Activity for {client}"
+        clients_to_show = [client]
+    else:
+        dff_grouped = dff_grouped[dff_grouped["client"].isin(top_clients)]
+        dff_grouped = (
+            dff_grouped.groupby(["timestamp", "client"])["count"].sum().reset_index()
+        )
+        title_text = f"Activity for top {n_clients} clients"
+        clients_to_show = top_clients
+
+    if dff_grouped.empty:
+        fig = px.area(
+            title=f"No activity available for {client}"
+            if client
+            else "No activity available",
+            template="plotly_white",
+        )
+        fig.update_layout(
+            xaxis_title="Date",
+            yaxis_title="Count",
+            annotations=[
+                dict(
+                    text="No data to display",
+                    x=0.5,
+                    y=0.5,
+                    xref="paper",
+                    yref="paper",
+                    showarrow=False,
+                )
+            ],
+        )
+        return fig
+
+    all_times = pd.date_range(
+        dff_grouped["timestamp"].min(), dff_grouped["timestamp"].max(), freq="h"
+    )
+    full_index = pd.MultiIndex.from_product(
+        [all_times, clients_to_show], names=["timestamp", "client"]
+    )
+    pivot_df = (
+        dff_grouped.set_index(["timestamp", "client"])
+        .reindex(full_index, fill_value=0)
+        .reset_index()
+    )
+
+    default_colors = px.colors.qualitative.Plotly
+    client_color_map = dict(zip(top_clients, itertools.cycle(default_colors)))
+
+    fig = px.area(
+        pivot_df,
+        x="timestamp",
+        y="count",
+        color="client",
+        line_group="client",
+        title=title_text,
+        color_discrete_map=client_color_map,
+        template="plotly_white",
+        labels={"timestamp": "Date", "count": "Count", "client": "Client IP"},
+    )
+
+    fig.update_traces(
+        mode="lines",
+        line_shape="spline",
+        line=dict(width=0.2),
+        stackgroup="one",
+        connectgaps=False,
+    )
+
+    fig.update_layout(
+        legend=dict(orientation="h", yanchor="top", y=-0.4, xanchor="center", x=0.5)
+    )
+
+    del dff_grouped, pivot_df
+    gc.collect()
+
+    return fig

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/piholelongtermstats/process.py

@@ -1,5 +1,5 @@
 ## Author :  Davis T. Daniel
-## PiHoleLongTermStats v.0.2.0
+## PiHoleLongTermStats v.0.2.2
 ## License :  MIT
 
 import re

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/piholelongtermstats/stats.py

@@ -1,5 +1,5 @@
 ## Author :  Davis T. Daniel
-## PiHoleLongTermStats v.0.2.0
+## PiHoleLongTermStats v.0.2.2
 ## License :  MIT
 
 import logging

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/piholelongtermstats.egg-info/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: piholelongtermstats
-Version: 0.2.0
+Version: 0.2.2
 Summary: A dashboard to explore long-term DNS query data from Pi-hole FTL database files.
 Author-email: Davis Thomas Daniel <davisthomasdaniel@gmail.com>
 Maintainer-email: Davis Thomas Daniel <davisthomasdaniel@gmail.com>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/davistdaniel/PiHoleLongTermStats
-Project-URL: Documentation, https://readthedocs.org
+Project-URL: Documentation, https://github.com/davistdaniel/PiHoleLongTermStats
 Project-URL: Repository, https://github.com/davistdaniel/PiHoleLongTermStats.git
 Project-URL: Bug Tracker, https://github.com/davistdaniel/PiHoleLongTermStats/issues
 Keywords: dashboard,pihole,visualization,plotly,dash
@@ -26,7 +26,7 @@ Requires-Dist: twine==6.2.0; extra == "develop"
 Requires-Dist: pytest-cov==7.0.0; extra == "develop"
 Dynamic: license-file
 
-# Pi Hole Long Term Statistics v.0.2.0
+# Pi Hole Long Term Statistics v.0.2.2
 
 A dashboard built with **Dash** and **Plotly** to explore long-term DNS query data from **Pi-hole v.6** FTL database files. Visualize allowed vs blocked domains, top clients, and query trends over time. I originally made this for my own use, but if you find it useful, a ⭐ would be awesome!
 

{piholelongtermstats-0.2.0 → piholelongtermstats-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "piholelongtermstats"
-version = "0.2.0"
+version = "0.2.2"
 dependencies = [
     "dash==3.0.4",
     "pandas==2.2.3",
@@ -34,7 +34,7 @@ develop = [
 
 [project.urls]
 Homepage = "https://github.com/davistdaniel/PiHoleLongTermStats"
-Documentation = "https://readthedocs.org"
+Documentation = "https://github.com/davistdaniel/PiHoleLongTermStats"
 Repository = "https://github.com/davistdaniel/PiHoleLongTermStats.git"
 "Bug Tracker" = "https://github.com/davistdaniel/PiHoleLongTermStats/issues"
 

piholelongtermstats-0.2.0/piholelongtermstats/__init__.py

@@ -1,3 +0,0 @@
-## Author :  Davis T. Daniel
-## PiHoleLongTermStats v.0.2.0
-## License :  MIT

piholelongtermstats-0.2.0/piholelongtermstats/plot.py

@@ -1,144 +0,0 @@
-## Author :  Davis T. Daniel
-## PiHoleLongTermStats v.0.2.0
-## License :  MIT
-
-import logging
-import pandas as pd
-import gc
-
-
-def generate_plot_data(df, n_clients, n_domains):
-    """Generate plot data"""
-
-    logging.info("Generating plot data...")
-
-    def shorten(s):
-        return s if len(s) <= 45 else f"{s[:20]}...{s[-20:]}"
-
-    top_clients = df["client"].value_counts().nlargest(n_clients).index
-    top_clients_stacked = (
-        df[df["client"].isin(top_clients)]
-        .groupby(["client", "status_type"])
-        .size()
-        .reset_index(name="count")
-    )
-    top_clients_stacked["client"] = pd.Categorical(
-        top_clients_stacked["client"],
-        categories=top_clients_stacked.groupby("client")["count"]
-        .sum()
-        .sort_values(ascending=False)
-        .index,
-        ordered=True,
-    )
-    top_clients_stacked = top_clients_stacked.sort_values(
-        ["client", "count"], ascending=[True, False]
-    )
-    logging.info("Generated plot data for top clients.")
-
-    # plot data for allowed and blocked domains
-    tmp_blocked = df[df["status_type"] == "Blocked"].copy()
-    tmp_blocked["domain"] = tmp_blocked["domain"].apply(shorten)
-
-    blocked_df = (
-        tmp_blocked["domain"]
-        .value_counts()
-        .nlargest(n_domains)
-        .reset_index()
-        .rename(columns={"index": "Count", "domain": "Domain"})
-    )
-
-    tmp_allowed = df[df["status_type"] == "Allowed"].copy()
-    tmp_allowed["domain"] = tmp_allowed["domain"].apply(shorten)
-
-    allowed_df = (
-        tmp_allowed["domain"]
-        .value_counts()
-        .nlargest(n_domains)
-        .reset_index()
-        .rename(columns={"index": "Count", "domain": "Domain"})
-    )
-
-    logging.info("Generated plot data for allowed and blocked domains.")
-
-    # plot data for reply time over days
-    reply_time_df = (
-        df.groupby("date")["reply_time"]
-        .mean()
-        .mul(1000)
-        .reset_index(name="reply_time_ms")
-    )
-
-    logging.info("Generated plot data for reply time plot")
-    client_list = df["client"].unique().tolist()
-
-    # plot data for doman-client scatter. take minimum from n_domains or n_clients
-    top_clients = df["client"].value_counts().nlargest(min(n_domains, n_clients)).index
-    top_domains = df["domain"].value_counts().nlargest(min(n_domains, n_clients)).index
-
-    df_top = df.loc[
-        df["client"].isin(top_clients) & df["domain"].isin(top_domains)
-    ].copy()
-    df_top.loc[:, "domain"] = df_top["domain"].apply(shorten)
-
-    client_domain_scatter_df = (
-        df_top.groupby(["client", "domain", "status_type"])
-        .size()
-        .reset_index(name="count")
-        .sort_values(by="count")
-    )
-
-    # heatmap
-    order = [
-        "Monday",
-        "Tuesday",
-        "Wednesday",
-        "Thursday",
-        "Friday",
-        "Saturday",
-        "Sunday",
-    ]
-
-    day_hour_heatmap = (
-        df.groupby(["day_name", "hour"])
-        .size()
-        .reset_index(name="count")
-        .pivot(index="day_name", columns="hour", values="count")
-        .fillna(0)
-        .reindex(order)
-    )
-
-    blocked_day_hour_heatmap = (
-        tmp_blocked.groupby(["day_name", "hour"])
-        .size()
-        .reset_index(name="count")
-        .pivot(index="day_name", columns="hour", values="count")
-        .fillna(0)
-        .reindex(order)
-    )
-
-    allowed_day_hour_heatmap = (
-        tmp_allowed.groupby(["day_name", "hour"])
-        .size()
-        .reset_index(name="count")
-        .pivot(index="day_name", columns="hour", values="count")
-        .fillna(0)
-        .reindex(order)
-    )
-
-    del df_top, top_clients, top_domains, tmp_allowed, tmp_blocked
-    gc.collect()
-
-    logging.info("Plot data generation complete")
-
-    return {
-        "top_clients_stacked": top_clients_stacked,
-        "blocked_df": blocked_df,
-        "allowed_df": allowed_df,
-        "reply_time_df": reply_time_df,
-        "client_list": client_list,
-        "data_span_days": (df["timestamp"].max() - df["timestamp"].min()).days,
-        "client_domain_scatter_df": client_domain_scatter_df,
-        "day_hour_heatmap": day_hour_heatmap,
-        "blocked_day_hour_heatmap": blocked_day_hour_heatmap,
-        "allowed_day_hour_heatmap": allowed_day_hour_heatmap,
-    }