add the task4 ...

.github/workflows/ci.yml

@@ -10,7 +10,7 @@ jobs:
   test:
     runs-on: ubuntu-latest
     container:
-      image: python:3.14-slim # prebuilt Python 3.14 container
+      image: python:3.13.1-slim #
 
     steps:
       - name: Checkout repository

.github/workflows/codeql.yml

@@ -1,44 +0,0 @@
-name: "CodeQL"
-
-on:
-  push:
-    branches: [main, master]
-  pull_request:
-    branches: [main, master]
-  schedule:
-    - cron: "0 3 * * 0" # weekly scan on Sunday 03:00 UTC
-
-jobs:
-  analyze:
-    name: Analyze (CodeQL)
-    runs-on: ubuntu-latest
-    permissions:
-      actions: read
-      contents: read
-      security-events: write
-    strategy:
-      fail-fast: false
-      matrix:
-        language: ["python"]
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Initialize CodeQL
-        uses: github/codeql-action/init@v2
-        with:
-          languages: ${{ matrix.language }}
-          # If you have custom queries, add them here:
-          # queries: ./codeql-queries
-          # Or disable default queries: queries: []
-          config-file: .github/codeql/codeql-config.yml # optional
-
-      - name: Autobuild
-        uses: github/codeql-action/autobuild@v2
-
-      - name: Run CodeQL analysis
-        uses: github/codeql-action/analyze@v2
-        with:
-          # If you specified queries in init, they will be used.
-          output: sarif/codeql-results.sarif

.vscode/settings.json

@@ -0,0 +1,35 @@
+{
+  // Python configuration
+  "python.analysis.extraPaths": ["./src", "./insurance_analytics"],
+  "python.testing.unittestArgs": ["-v", "-s", "./tests", "-p", "test_*.py"],
+  "python.testing.unittestEnabled": true,
+  "python.languageServer": "Pylance",
+
+  // File watching & search optimization
+  // "files.watcherExclude": {
+  //   "**/node_modules/**": true,
+  //   "**/.git/**": true,
+  //   "**/.venv/**": true,
+  //   "**/dist/**": true,
+  //   "**/build/**": true
+  // },
+  // "search.exclude": {
+  //   "**/node_modules": true,
+  //   "**/.venv": true,
+  //   "**/dist": true,
+  //   "**/build": true
+  // },
+
+  // // Editor performance tweaks
+  // "editor.formatOnSave": false,
+  // "editor.formatOnType": false,
+  // "editor.formatOnPaste": false,
+  // "editor.minimap.enabled": false,
+  // "workbench.colorTheme": "Default Dark+",
+
+  // Git optimization for large repos
+  "git.enabled": false,
+
+  // Telemetry off
+  "telemetry.telemetryLevel": "off"
+}

configs/dvc_remote.yaml

@@ -1,7 +0,0 @@
-stages:
-  track_raw_data:
-    cmd: dvc add data/raw/MachineLearningRating_v3.txt
-    deps:
-      - data/raw/MachineLearningRating_v3.txt
-    outs:
-      - data/raw/MachineLearningRating_v3.txt.dvc

configs/hypotheses.yaml

@@ -0,0 +1,52 @@
+# hypotheses.yaml
+# List of hypothesis entries. Each entry must contain:
+# - feature: column name in dataframe
+# - kpi: KPI column name (ClaimFrequency, ClaimSeverity, Margin)
+# - test_type: chi2 | t | anova
+# - description: short human-readable description
+
+hypotheses:
+  - feature: Province
+    kpi: ClaimFrequency
+    test_type: chi2
+    description: Claim frequency differences across provinces
+
+  - feature: Province
+    kpi: ClaimSeverity
+    test_type: anova
+    description: Claim severity differences across provinces
+
+  - feature: Province
+    kpi: Margin
+    test_type: anova
+    description: Margin differences across provinces
+
+  - feature: PostalCode
+    kpi: ClaimFrequency
+    test_type: chi2
+    description: Claim frequency differences across zip codes
+
+  - feature: PostalCode
+    kpi: ClaimSeverity
+    test_type: anova
+    description: Claim severity differences across zip codes
+
+  - feature: PostalCode
+    kpi: Margin
+    test_type: anova
+    description: Margin differences across zip codes
+
+  - feature: Gender
+    kpi: ClaimFrequency
+    test_type: chi2
+    description: Claim frequency differences by gender
+
+  - feature: Gender
+    kpi: ClaimSeverity
+    test_type: anova
+    description: Claim severity differences by gender
+
+  - feature: Gender
+    kpi: Margin
+    test_type: anova
+    description: Margin differences by gender