init

src/app.py

@@ -0,0 +1,257 @@
+from flask import Flask, render_template
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+import statsmodels.api as sm
+import numpy as np
+import datetime
+from sklearn.linear_model import LinearRegression
+import json
+from stats import generate_stats
+from player_table import generate_player_table
+import constants
+
+app = Flask(__name__)
+
+
+def get_data_frame(filename):
+    df = pd.read_csv(filename)
+    df["Date"] = pd.to_datetime(df["Date"], dayfirst=True)
+    df = df.sort_values("Date").reset_index(drop=True)
+    return df
+
+
+def build_hovertext(df, attendance_columns):
+    return df[attendance_columns].apply(
+        lambda row: ", ".join(
+            [
+                player
+                for player in attendance_columns
+                if row[player] == 1
+            ]
+        ) or "No attendance",
+        axis=1
+    )
+
+
+def generate_weekly_attendance_calendar(df):
+    # Compute ISO year/week and attendance
+    df["Year"] = df["Date"].dt.isocalendar().year
+    df["Week"] = df["Date"].dt.isocalendar().week
+
+    attendee_columns = [
+        col for col in df.columns if col not in {
+            "Date", "Relative Position", "Number of Players",
+            "Number of Teams", "Attendees", "Year", "Week", "Year-Week"
+        }
+    ]
+
+    df["Attended"] = df[attendee_columns].sum(axis=1) > 0
+    weekly_attendance = df.groupby(["Year", "Week"])[
+        "Attended"].any().astype(int).reset_index()
+
+    # Build full year/week grid
+    all_years = sorted(df["Year"].unique())
+    all_weeks = list(range(1, 53))
+
+    grid = []
+    for year in all_years:
+        for week in all_weeks:
+            grid.append({"Year": year, "Week": week})
+
+    calendar = pd.DataFrame(grid)
+    calendar = calendar.merge(weekly_attendance, on=[
+                              "Year", "Week"], how="left").fillna(0)
+    calendar["Attended"] = calendar["Attended"].astype(int)
+
+    # Plot
+    fig = go.Figure(data=go.Heatmap(
+        x=calendar["Week"],
+        y=calendar["Year"],
+        z=calendar["Attended"],
+        colorscale=constants.ATTENDANCE_COLORSCHEME,
+        zmin=0,
+        zmax=1,
+        showscale=False
+    ))
+
+    fig.update_layout(
+        title="Pub Quiz Attendance Calendar (Weekly)",
+        xaxis_title="Week Number",
+        yaxis_title="Year",
+        xaxis=dict(tickmode="linear", dtick=4),
+        template="plotly_white",
+        height=180 + len(all_years) * 40
+    )
+
+    return fig
+
+
+def generate_relative_position_over_time(df):
+    df["Date_ordinal"] = df["Date"].map(pd.Timestamp.toordinal)
+
+    X = sm.add_constant(df["Date_ordinal"])
+    y = df["Relative Position"]
+
+    model = sm.OLS(y, X).fit()
+    df["BestFit"] = model.predict(X)
+
+    intercept = model.params["const"]
+    slope = model.params["Date_ordinal"]
+
+    target_value = 0.08
+
+    predicted_ordinal = (target_value - intercept) / slope
+
+    min_ordinal = df["Date_ordinal"].min()
+    max_ordinal = df["Date_ordinal"].max()
+
+    if predicted_ordinal > max_ordinal:
+        extended_ordinals = np.linspace(min_ordinal, predicted_ordinal, 100)
+    else:
+        extended_ordinals = np.linspace(min_ordinal, max_ordinal, 100)
+
+    extended_bestfit = intercept + slope * extended_ordinals
+
+    extended_dates = [datetime.date.fromordinal(
+        int(x)) for x in extended_ordinals]
+
+    df["Attendees"] = build_hovertext(df, constants.PLAYER_NAME_COLUMNS)
+
+    fig = px.line(
+        df,
+        x="Date",
+        y="Relative Position",
+        title="Quiz Position Over Time with Extended Trendline",
+        hover_data={"Attendees": True}
+    )
+
+    fig.add_scatter(
+        x=extended_dates,
+        y=extended_bestfit,
+        mode="lines",
+        name="Extended Trendline",
+        line=dict(dash="dot", color="red")
+    )
+
+    fig.update_yaxes(range=[0, 1], tickformat=".2f")
+    return fig
+
+
+def generate_visualisations(df):
+    feature_columns = [
+        col
+        for col in df.columns
+        if col in constants.FEATURE_COLUMNS
+    ]
+    x = df[feature_columns]
+    y = df["Relative Position"]
+
+    model = LinearRegression()
+    model.fit(x, y)
+
+    plots = {}
+
+    plots["relative_pos_over_time"] = json.dumps(
+        generate_relative_position_over_time(df),
+        cls=plotly.utils.PlotlyJSONEncoder
+    )
+
+    df_line = df.melt(
+        id_vars="Date",
+        value_vars=["Absolute Position", "Number of Teams"],
+        var_name="Metric",
+        value_name="Value"
+    )
+    fig11 = px.line(
+        df_line,
+        x='Date',
+        y='Value',
+        color='Metric',
+        title='Absolute Position and Total Number of Teams Over Time'
+    )
+    plots["absolute_pos_over_time"] = json.dumps(
+        fig11, cls=plotly.utils.PlotlyJSONEncoder
+    )
+
+# 2. Number of players vs position with regression line
+    fig2 = px.scatter(
+        df,
+        x="Number of Players",
+        y="Relative Position",
+        trendline="ols",
+        title="Players vs Position (%)",
+    )
+    fig2.update_xaxes(dtick=1)
+    plots["players_vs_position"] = json.dumps(
+        fig2, cls=plotly.utils.PlotlyJSONEncoder)
+
+# 3. Player participation heatmap
+    df_players = df[constants.PLAYER_NAME_COLUMNS]
+    fig3 = px.imshow(
+        df_players.T,
+        labels=dict(x="Games", y="Player", color="Present"),
+        title="Player Participation Heatmap",
+        color_continuous_scale=constants.ATTENDANCE_COLORSCHEME,
+        zmin=0,
+        zmax=1,
+        aspect="auto"
+    )
+    fig3.update_coloraxes(
+        colorbar=dict(
+            tickvals=[0, 1],
+            ticktext=["Absent", "Present"],
+            lenmode="pixels",
+            len=300,
+        )
+    )
+    fig3.update_layout(
+        template="seaborn",
+        height=600,
+        yaxis=dict(
+            tickmode="array",
+            tickvals=list(range(len(df_players.columns))),
+            ticktext=df_players.columns
+        )
+    )
+    plots["player_participation"] = json.dumps(
+        fig3, cls=plotly.utils.PlotlyJSONEncoder)
+
+# 4. Calendar view
+    plots["calendar"] = json.dumps(
+        generate_weekly_attendance_calendar(df),
+        cls=plotly.utils.PlotlyJSONEncoder
+    )
+
+# 5. Coefficient bar chart
+    coefficients = pd.Series(model.coef_, index=x.columns).sort_values()
+    fig5 = px.bar(
+        coefficients,
+        orientation="h",
+        labels={"value": "Coefficient", "index": "Feature"},
+        title="Linear Regression Coefficients",
+    )
+    plots["coefficients"] = json.dumps(
+        fig5, cls=plotly.utils.PlotlyJSONEncoder)
+
+    return plots
+
+
+@app.route("/")
+def index():
+    df = get_data_frame("data.csv")
+    stats = generate_stats(df)
+    player_table = generate_player_table(df)
+    plots = generate_visualisations(df)
+    return render_template(
+        "index.html",
+        plots=plots,
+        stats=stats,
+        player_table=player_table
+    )
+
+
+if __name__ == "__main__":
+    import plotly
+
+    app.run(debug=True)

src/constants.py

@@ -0,0 +1,32 @@
+PLAYER_NAME_COLUMNS = [
+    "Ciaran",
+    "Jay",
+    "Sam",
+    "Drew",
+    "Theo",
+    "Tom",
+    "Ellora",
+    "Chloe",
+    "Jamie",
+    "Christine"
+]
+
+FEATURE_COLUMNS = {
+    "Number of Players",
+    "Number of Teams",
+    "Points on Scattergories",
+    "Ciaran",
+    "Jay",
+    "Sam",
+    "Drew",
+    "Theo",
+    "Tom",
+    "Ellora",
+    "Chloe",
+    "Jamie",
+    "Christine"
+}
+
+ATTENDANCE_COLORSCHEME = [
+    [0, "#E4ECF6"], [1, "#636EFA"]
+]

src/player_table.py

@@ -0,0 +1,20 @@
+from constants import PLAYER_NAME_COLUMNS
+
+
+def generate_player_table(df):
+    header = [["Name", "Appearances", "Spent"]]
+
+    player_stats = [
+        (name, df[name].sum())
+        for name in df.columns
+        if name in PLAYER_NAME_COLUMNS
+    ]
+    player_stats.sort(key=lambda x: x[1], reverse=True)
+    total = sum(n for name, n in player_stats)
+    body = [
+        [name, n, f"£{n * 3:.2f}"]
+        for name, n in player_stats
+    ]
+    footer = [["Total", total, f"£{total * 3:.2f}"]]
+
+    return (header + body + footer)

src/stats.py

@@ -0,0 +1,53 @@
+import constants
+
+
+def get_max_team_streak(dates):
+    max_streak = current_streak = 1
+    for i in range(1, len(dates)):
+        if (dates[i] - dates[i-1]).days == 7:
+            current_streak += 1
+        else:
+            current_streak = 1
+        max_streak = max(current_streak, max_streak)
+
+    # TODO: Show dates
+    return f"{max_streak} weeks"
+
+
+def get_max_player_streak(df):
+    names = [col for col in df.columns if col in constants.PLAYER_NAME_COLUMNS]
+    max_streak = 1
+    max_name = names[0]
+    for name in names:
+        local_max = 1
+        current = 0
+        for attendance in df[name]:
+            if attendance:
+                current += 1
+            else:
+                local_max = max(local_max, current)
+                current = 0
+
+        local_max = max(local_max, current)
+        if local_max > max_streak:
+            max_streak = local_max
+            max_name = name
+
+    return f"{max_streak} ({max_name})"
+
+
+def generate_stats(df):
+    stats = {}
+    n = len(df["Date"])
+
+    stats["Number of quizes played"] = n
+    avg_players = df["Number of Players"].sum() / n
+    stats["Average number of players"] = f"{avg_players:.2f}"
+    avg_teams = df["Number of Teams"].sum() / n
+    stats["Average number of teams"] = f"{avg_teams:.2f}"
+    p = df["Relative Position"].sum()*100 / n
+    stats["Average relative position"] = f"{p:.2f}th percentile"
+    stats["Max consecutive week streak"] = get_max_team_streak(df["Date"])
+    stats["Max consecutive player streak"] = get_max_player_streak(df)
+
+    return stats

src/templates/index.html

@@ -0,0 +1,80 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+    <title>Pub Quiz Dashboard</title>
+    <script src="https://cdn.plot.ly/plotly-3.0.1.min.js" charset="utf-8"></script>
+    <script src="https://cdn.tailwindcss.com"></script>
+</head>
+
+<body class="flex flex-col items-center">
+    <h1 class="text-center font-sans text-4xl p-10">📊 Pub Quiz Dashboard</h1>
+
+    <div class="w-3/4">
+        <h2 class="text-2xl mb-4">Stats</h2>
+        <div class="flex flex-col items-center">
+            <div class="rounded-md border border-black w-2/5 p-4 m-8">
+                <ul class="space-y-2">
+                    {% for key, data in stats.items() %}
+                    <li id="{{ key }}" class="flex justify-between">
+                        <span>{{ key }}:</span>
+                        <span class="flex-grow border-b border-dotted mx-2"></span>
+                        <span>{{ data }}</span>
+                    </li>
+                    {% endfor %}
+                </ul>
+            </div>
+        </div>
+    </div>
+
+    <div class="w-3/4 flex flex-col items-center overflow-x-auto">
+        <table class="w-1/2 text-sm text-gray-700 border-separate border-spacing-0 rounded-xl bg-clip-border shadow-md">
+            <thead
+                class="bg-gray-100 text-xs font-semibold uppercase tracking-wider text-gray-700 border-b border-gray-300">
+                <tr>
+                    {% for heading in player_table[0] %}
+                    <th scope="col" class="px-6 py-4 w-1/3 border-b border-blue-grey-100 bg-blue-grey-50
+                        {% if loop.index == 1 %} text-left
+                        {% elif loop.index == 2 %} text-center
+                        {% else %} text-right
+                        {% endif %}
+                        ">
+                        {{ heading }}
+                    </th>
+                    {% endfor %}
+                </tr>
+            </thead>
+            <tbody class="divide-y divide-gray-200">
+                {% for row in player_table[1:] %}
+                <tr class="bg-white">
+                    {% for data in row %}
+                    <td class="px-6 py-4 whitespace-nowrap text-sm font-medium text-gray-900 antialiased leading-normal border-b border-blue-grey-50
+                    {% if loop.index == 1 %} text-left
+                    {% elif loop.index == 2 %} text-center
+                    {% else %} text-right
+                    {% endif %}">
+                        {{ data }}
+                    </td>
+                    {% endfor %}
+                </tr>
+                {% endfor %}
+            </tbody>
+        </table>
+    </div>
+
+    <div class="w-3/4">
+        <h2 class="text-2xl">Plots</h2>
+        {% for key, plot in plots.items() %}
+        <div class="m-8 bg-white p-8 rounded-md shadow-md">
+            <div id="{{ key }}"></div>
+            <script>
+                var figure = {{plot | safe }};
+                Plotly.newPlot("{{ key }}", figure.data, figure.layout);
+            </script>
+        </div>
+        {% endfor %}
+    </div>
+
+</body>
+
+</html>