Update: 2026-07-06 17:00:43

2026-07-06 17:00:43 +03:00
parent 61cb615ae7
commit e42d700245
21 changed files with 3212 additions and 119 deletions
@@ -0,0 +1,120 @@
+import { PricingTier, RegressionResult, RideSample } from './types';
+import {
+  robustMultipleLinearRegression,
+  calcRMSE,
+  calcRSquared,
+  detectMinimumFare,
+} from '../utils/math';
+import { mean } from 'simple-statistics';
+
+/**
+ * Run multiple linear regression on each pricing tier.
+ * Detects minimum fare and computes RMSE/R².
+ */
+export function analyzeTier(tier: PricingTier): PricingTier {
+  const samples = tier.samples;
+  if (samples.length < 5) {
+    tier.regression = null;
+    return tier;
+  }
+
+  // Primary model: price = baseFare + kmRate * dist + minRate * dur
+  // We use robust regression to strip out surge outliers and find the floor price
+  const mlrResult = robustMultipleLinearRegression(
+    samples.map(s => ({
+      distance_km: s.distance_km,
+      duration_min: s.duration_min,
+      price: s.price,
+    }))
+  );
+
+  if (!mlrResult) {
+    tier.regression = null;
+    return tier;
+  }
+
+  // Predict and compute RMSE/R²
+  const actualPrices = samples.map(s => s.price);
+  const predictedPrices = samples.map(s =>
+    mlrResult.baseFare +
+    mlrResult.kmRate * s.distance_km +
+    mlrResult.minRate * s.duration_min
+  );
+
+  const rmse = calcRMSE(actualPrices, predictedPrices);
+  const rSquared = calcRSquared(actualPrices, predictedPrices);
+
+  // Detect minimum fare
+  const minFare = detectMinimumFare(
+    samples.map(s => s.distance_km),
+    samples.map(s => s.price),
+    mlrResult.kmRate
+  );
+
+  // If minFare is detected and the short-ride residuals improve,
+  // apply minFare-adjusted model
+  let hasMinFare = false;
+  let adjustedRMSE = rmse;
+  let adjustedRSquared = rSquared;
+
+  if (minFare && minFare > 0) {
+    const adjustedPredicted = samples.map(s => {
+      const raw = mlrResult.baseFare + mlrResult.kmRate * s.distance_km + mlrResult.minRate * s.duration_min;
+      return Math.max(raw, minFare);
+    });
+    const adjRmse = calcRMSE(actualPrices, adjustedPredicted);
+    const adjRsq = calcRSquared(actualPrices, adjustedPredicted);
+
+    // If minimum fare improves the fit, use it
+    if (adjRmse < rmse) {
+      hasMinFare = true;
+      adjustedRMSE = adjRmse;
+      adjustedRSquared = adjRsq;
+    }
+  }
+
+  tier.regression = {
+    baseFare: mlrResult.baseFare,
+    kmRate: mlrResult.kmRate,
+    minRate: mlrResult.minRate,
+    minFare: minFare || 0,
+    rmse: adjustedRMSE,
+    rSquared: adjustedRSquared,
+    sampleCount: samples.length,
+    hasMinFare,
+  };
+
+  return tier;
+}
+
+/**
+ * Run regression on all tiers.
+ */
+export function analyzeAllTiers(tiers: PricingTier[]): PricingTier[] {
+  return tiers.map(tier => analyzeTier(tier));
+}
+
+/**
+ * Simple distance-only regression for comparison.
+ * price = kmRate * dist
+ */
+export function distanceOnlyRegression(
+  samples: RideSample[]
+): { kmRate: number; rmse: number } | null {
+  if (samples.length < 3) return null;
+
+  const distances = samples.map(s => s.distance_km);
+  const prices = samples.map(s => s.price);
+
+  // Simple average of price/km
+  const ratios = distances.map((d, i) => d > 0 ? prices[i] / d : 0)
+    .filter(r => r > 0 && isFinite(r));
+
+  if (ratios.length < 3) return null;
+
+  const kmRate = mean(ratios);
+  const predicted = distances.map(d => kmRate * d);
+  const rmse = calcRMSE(prices, predicted);
+
+  return { kmRate, rmse };
+}