Initial commit

backend/tests/test_analysis.py

@@ -0,0 +1,80 @@
+from fastapi.testclient import TestClient
+from main import app
+
+client = TestClient(app)
+
+def test_outlier_detection_univariate():
+    # Data with one clear outlier (100)
+    data = [
+        {"val": 10}, {"val": 11}, {"val": 12}, {"val": 10}, {"val": 100}
+    ]
+    request_data = {
+        "data": data,
+        "columns": ["val"],
+        "method": "univariate"
+    }
+    
+    response = client.post("/api/v1/analysis/detect-outliers", json=request_data)
+    assert response.status_code == 200
+    json_resp = response.json()
+    assert json_resp["total_count"] == 1
+    assert json_resp["outliers"][0]["index"] == 4
+    assert "IQR bounds" in json_resp["outliers"][0]["reasons"][0]
+
+def test_outlier_detection_multivariate():
+    # Data with a multivariate anomaly
+    data = [
+        {"x": 1, "y": 1}, {"x": 1.1, "y": 0.9}, {"x": 0.9, "y": 1.1},
+        {"x": 10, "y": 10} # Anomaly
+    ]
+    request_data = {
+        "data": data,
+        "columns": ["x", "y"],
+        "method": "multivariate"
+    }
+    
+    response = client.post("/api/v1/analysis/detect-outliers", json=request_data)
+    assert response.status_code == 200
+    json_resp = response.json()
+    assert json_resp["total_count"] >= 1
+
+def test_feature_importance():
+    data = [
+        {"x1": 1, "x2": 10, "y": 2},
+        {"x1": 2, "x2": 20, "y": 4},
+        {"x1": 3, "x2": 30, "y": 6},
+        {"x1": 4, "x2": 40, "y": 8},
+        {"x1": 5, "x2": 50, "y": 10}
+    ]
+    request_data = {
+        "data": data,
+        "features": ["x1", "x2"],
+        "target": "y"
+    }
+    response = client.post("/api/v1/analysis/feature-importance", json=request_data)
+    assert response.status_code == 200
+    json_resp = response.json()
+    assert len(json_resp["importances"]) == 2
+    assert "feature" in json_resp["importances"][0]
+    assert "score" in json_resp["importances"][0]
+
+def test_run_regression():
+    data = [
+        {"x": 1, "y": 2.1},
+        {"x": 2, "y": 3.9},
+        {"x": 3, "y": 6.2},
+        {"x": 4, "y": 8.1},
+        {"x": 5, "y": 10.3}
+    ]
+    request_data = {
+        "data": data,
+        "x_features": ["x"],
+        "y_target": "y",
+        "model_type": "linear"
+    }
+    response = client.post("/api/v1/analysis/run-regression", json=request_data)
+    assert response.status_code == 200
+    json_resp = response.json()
+    assert "results" in json_resp
+    assert json_resp["results"]["r_squared"] > 0.9
+    assert "const" in json_resp["results"]["coefficients"]

backend/tests/test_upload.py

@@ -0,0 +1,37 @@
+from fastapi.testclient import TestClient
+import pandas as pd
+import io
+import pyarrow as pa
+from main import app
+
+client = TestClient(app)
+
+def test_health_check():
+    response = client.get("/health")
+    assert response.status_code == 200
+    assert response.json() == {"status": "ok", "service": "backend"}
+
+def test_upload_csv():
+    # Create a dummy CSV
+    csv_content = "name,age\nAlice,30\nBob,25"
+    file = ("test.csv", csv_content, "text/csv")
+    
+    response = client.post("/api/v1/upload", files={"file": file})
+    
+    assert response.status_code == 200
+    assert response.headers["content-type"] == "application/vnd.apache.arrow.stream"
+    assert "X-Column-Metadata" in response.headers
+    
+    # Verify Arrow data
+    buffer = io.BytesIO(response.content)
+    with pa.ipc.open_stream(buffer) as reader:
+        table = reader.read_all()
+        df = table.to_pandas()
+        assert df.shape == (2, 2)
+        assert list(df.columns) == ["name", "age"]
+
+def test_upload_invalid_format():
+    file = ("test.txt", "invalid content", "text/plain")
+    response = client.post("/api/v1/upload", files={"file": file})
+    assert response.status_code == 400
+    assert "Only .xlsx, .xls and .csv files are supported" in response.json()["detail"]