init
This commit is contained in:
John Gatward
257
src/app.py
Normal file
257
src/app.py
Normal file
@@ -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)
|
||||
Reference in New Issue
Block a user