构建可解释的共享单车回归

from pathlib import Path
import base64, gzip, hashlib, json, platform
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import display, HTML
from datetime import datetime
from IPython.display import display as _display
def display(value):
    if isinstance(value,pd.DataFrame):
        table=value.to_html(max_rows=12,escape=True)
        style="<style>.vibeit-readable-table{max-width:100%;overflow-x:auto}.vibeit-readable-table table{width:max-content;max-width:none;border-collapse:collapse}.vibeit-readable-table td,.vibeit-readable-table th{white-space:nowrap!important;word-break:normal!important;overflow-wrap:normal!important}</style>"
        return _display(HTML(style+'<div class="vibeit-readable-table">'+table+'</div>'))
    return _display(value)
RECIPE_ID='ds05-bike-regression'
OUTPUT_DIR=Path.cwd()/"results"/RECIPE_ID
plt.rcParams.update({"figure.dpi":120,"font.size":10,"axes.spines.top":False,"axes.spines.right":False,
                      "axes.prop_cycle":plt.cycler(color=["#18785f","#416aa6","#bc6541","#9974a5"])})
print("Python:",platform.python_version(),"; NumPy:",np.__version__,"; Pandas:",pd.__version__)
print("Working folder:",Path.cwd())
print("Core data mode: embedded snapshot; no network requests")

Python: 3.13.13 ; NumPy: 2.5.3 ; Pandas: 3.0.6
Working folder: /Users/zhiluo/Developer/vibeit-cookbook/cookbook/downloads
Core data mode: embedded snapshot; no network requests

def load_snapshot(recipe_id, expected_sha256, snapshot_key):
    """Read embedded data from this notebook, including a renamed copy."""
    for path in sorted(Path.cwd().glob("*.ipynb")):
        try:
            notebook = json.loads(path.read_text(encoding="utf-8"))
            metadata = notebook.get("metadata", {}).get("vibeit_cookbook", {})
            blob = metadata.get("snapshots", {}).get(snapshot_key)
            if metadata.get("recipe_id") != recipe_id or not blob:
                continue
            if blob.get("sha256") != expected_sha256:
                continue
            raw = gzip.decompress(base64.b64decode(blob["gzip_base64"], validate=True))
            if hashlib.sha256(raw).hexdigest() != expected_sha256:
                raise ValueError("Embedded snapshot checksum mismatch: " + snapshot_key)
            return json.loads(raw)
        except (OSError, json.JSONDecodeError):
            continue
    raise FileNotFoundError(
        "Save/open the complete .ipynb in the active working folder. "
        "The embedded snapshot could not be located for " + recipe_id)

SNAPSHOT_HASHES={'bike': '99d075d1b2d3c2c9ce73f256dcc370081a51d1df60347f59674a8ed3edf92f92'}
def snapshot(key):
    return load_snapshot(RECIPE_ID,SNAPSHOT_HASHES[key],key)
print("Embedded snapshots:",list(SNAPSHOT_HASHES))

Embedded snapshots: ['bike']

def audit_numeric_table(frame,columns):
    """Audit observed rows; never silently impute or remove them."""
    if frame.empty or frame.index.has_duplicates:
        raise ValueError('Expected a nonempty table with unique row IDs')
    missing=[name for name in columns if name not in frame.columns]
    if missing:raise ValueError('Missing required columns: '+str(missing))
    values=frame[columns].to_numpy(dtype=float)
    if not np.isfinite(values).all():raise ValueError('Non-finite measurements; inspect missing values explicitly')
    return {'rows':len(frame),'features':len(columns),'finite':True,'duplicate_measurement_rows':int(frame[columns].duplicated().sum())}

print("Method ready: audit_numeric_table")

Method ready: audit_numeric_table

def ridge_fit_predict(train_values,train_target,test_values,penalty=1.0):
    """Scale using training statistics and solve ridge by an augmented least-squares system."""
    train_values=np.asarray(train_values,dtype=float);test_values=np.asarray(test_values,dtype=float)
    target=np.asarray(train_target,dtype=float)
    if train_values.ndim!=2 or len(train_values)==0 or target.shape!=(len(train_values),) or penalty<0:raise ValueError('Invalid training data or penalty')
    if test_values.ndim!=2 or train_values.shape[1]!=test_values.shape[1]:raise ValueError('Training/test feature dimensions differ')
    if not np.isfinite(train_values).all() or not np.isfinite(test_values).all() or not np.isfinite(target).all():raise ValueError('Non-finite training data')
    mean=train_values.mean(axis=0);scale=train_values.std(axis=0);scale=np.where(scale==0,1,scale)
    design=np.column_stack([np.ones(len(train_values)),(train_values-mean)/scale])
    test_design=np.column_stack([np.ones(len(test_values)),(test_values-mean)/scale])
    regularizer=np.sqrt(penalty)*np.eye(design.shape[1]);regularizer[0,0]=0
    coefficients=np.linalg.lstsq(np.vstack([design,regularizer]),np.r_[target,np.zeros(design.shape[1])],rcond=None)[0]
    return dict(predictions=test_design@coefficients,coefficients=coefficients,mean=mean,scale=scale,train_predictions=design@coefficients)

print("Method ready: ridge_fit_predict")

Method ready: ridge_fit_predict

def regression_metrics(truth,predictions):
    truth=np.asarray(truth,dtype=float);predictions=np.asarray(predictions,dtype=float)
    if truth.shape!=predictions.shape or truth.size==0 or not np.isfinite(truth-predictions).all():raise ValueError('Invalid regression comparison')
    error=predictions-truth;denominator=np.sum((truth-truth.mean())**2)
    return dict(mae=float(np.mean(np.abs(error))),rmse=float(np.sqrt(np.mean(error**2))),r_squared=float(1-np.sum(error**2)/denominator) if denominator>0 else float('nan'))

print("Method ready: regression_metrics")

Method ready: regression_metrics

def iso_datetimes(values):
    """Parse source ISO dates with the standard library; keep tables as ISO strings."""
    return [datetime.fromisoformat(str(value)) for value in values]

print("Method ready: iso_datetimes")

Method ready: iso_datetimes

bike=snapshot("bike")
frame=pd.DataFrame(bike["rows"],columns=bike["columns"])
frame["date"]=frame["dteday"].astype(str)
frame=frame.sort_values("date").reset_index(drop=True)
assert len(frame)==731 and frame["date"].is_unique
dates=iso_datetimes(frame.date)
assert all((b-a).total_seconds()==86400 for a,b in zip(dates,dates[1:]))
assert (frame["casual"]+frame["registered"]).eq(frame["cnt"]).all()
assert frame["cnt"].ge(0).all()
print("Complete daily observations:",len(frame),"; target: rentals/day")
display(frame[["date","cnt","temp","hum","windspeed"]].head(7))

Complete daily observations: 731 ; target: rentals/day

frame["elapsed_days"]=[(value-dates[0]).days for value in dates]
features=["temp","hum","windspeed","workingday","elapsed_days"]
audit_numeric_table(frame,features+["cnt"])
train=np.array([value.year==2011 for value in dates]);test=~train
assert train.sum()==365 and test.sum()==366
fig,ax=plt.subplots(figsize=(9,4));ax.plot(dates,frame.cnt,color="gray",lw=1)
ax.axvline(datetime(2012,1,1),color="red",linestyle="--",label="2011 fit / 2012 test")
ax.set(xlabel="Date",ylabel="Rentals/day",title="Chronological split and observed demand");ax.legend();plt.tight_layout();plt.show()

model=ridge_fit_predict(frame.loc[train,features].to_numpy(),frame.loc[train,"cnt"].to_numpy(),frame.loc[test,features].to_numpy(),penalty=1.0)
prediction=model["predictions"];truth=frame.loc[test,"cnt"].to_numpy(float)
metrics=regression_metrics(truth,prediction)
print("2012 held-out metrics:",metrics)
print("Negative predictions (not silently clipped):",int(np.sum(prediction<0)))
display(pd.DataFrame({"term":["intercept"]+features,"coefficient":model["coefficients"]}))
fig,ax=plt.subplots(figsize=(6,5));ax.scatter(truth,prediction,s=13,alpha=.5)
limit=[min(truth.min(),prediction.min()),max(truth.max(),prediction.max())];ax.plot(limit,limit,"k--")
ax.set(xlabel="Observed rentals/day",ylabel="Predicted rentals/day",title="2012 conditional predictions");plt.tight_layout();plt.show()

2012 held-out metrics: {'mae': 1245.3946847319723, 'rmse': 1479.994175429142, 'r_squared': 0.3134869093527851}
Negative predictions (not silently clipped): 0

	term	coefficient
0	intercept	3405.761644
1	temp	975.325148
2	hum	-273.416546
3	windspeed	-250.541176
4	workingday	-3.297354
5	elapsed_days	329.429847

residual=prediction-truth
fig,ax=plt.subplots(figsize=(9,4));ax.plot(iso_datetimes(frame.loc[test,"date"]),residual,lw=1)
ax.axhline(0,color="black",linestyle="--");ax.set(xlabel="Date in 2012",ylabel="Prediction − observation (rentals/day)",title="Chronological regression errors");plt.tight_layout();plt.show()

assert np.isclose(metrics["rmse"],np.linalg.norm(prediction-truth)/np.sqrt(len(truth)))
assert np.allclose(model["mean"],frame.loc[train,features].mean())
assert not {"casual","registered","cnt"}&set(features)
OUTPUT_DIR.mkdir(parents=True,exist_ok=True)
pd.DataFrame({"date":frame.loc[test,"date"],"observed_rentals":truth,"predicted_rentals":prediction,"error":residual}).to_csv(OUTPUT_DIR/"2012-predictions.csv",index=False)
(OUTPUT_DIR/"model.json").write_text(json.dumps({"features":features,"penalty":1.0,"training_year":2011,"test_year":2012,"mean":model["mean"].tolist(),"scale":model["scale"].tolist(),"coefficients":model["coefficients"].tolist(),"metrics":metrics},indent=2))
print("Training-only scale and metric checks passed; exports:",OUTPUT_DIR)

Training-only scale and metric checks passed; exports: /Users/zhiluo/Developer/vibeit-cookbook/cookbook/downloads/results/ds05-bike-regression

RUN_ONLINE_UPDATE=False
if RUN_ONLINE_UPDATE:
    import requests
    try:
        response=requests.get('https://archive.ics.uci.edu/dataset/275',timeout=20)
        response.raise_for_status()
        print("Source:",response.url)
        print(response.text[:700])
    except requests.RequestException as error:
        print("Online extension unavailable:",type(error).__name__,str(error)[:160])
else:
    print("Online extension skipped; embedded core data unchanged")

Online extension skipped; embedded core data unchanged