final

model.py

@@ -31,7 +31,6 @@ class CreatinineMeasurement(BaseModel):
 class PatientData(BaseModel):
     age: float = Field(ge=0)
     sex: str = Field(pattern="^[mf]$")
-    aki: str = Field(pattern="^[yn]$")
     measurements: List[CreatinineMeasurement]
 
     @field_validator("measurements")
@@ -66,9 +65,7 @@ def validate_data(df: pd.DataFrame) -> None:
                     }
                 )
 
-        PatientData(
-            age=row["age"], sex=row["sex"], aki=row["aki"], measurements=measurements
-        )
+        PatientData(age=row["age"], sex=row["sex"], measurements=measurements)
 
 
 def main():

requirements.txt

--f https://download.pytorch.org/whl/torch_stable.html
-numpy==1.26.4
-torch==2.3.1+cpu
+torch
 pandas
 tqdm
 scikit-learn

test/test_data.py

-from pathlib import Path
-
 import pandas as pd
 import pytest
-from sklearn.metrics import fbeta_score
 
 import model
 
@@ -24,12 +21,6 @@ def test_preprocess_features():
     assert result["sex"].dtype == int
 
 
-def test_validate_data_missing_columns():
-    test_data = pd.DataFrame({"age": [30, 40], "sex": ["M", "F"]})
-    with pytest.raises(KeyError):
-        model.validate_data(test_data)
-
-
 def test_validate_data_negative_age():
     test_data = pd.DataFrame(
         {

test/test_model.py

@@ -10,7 +10,7 @@ import model
 
 def test_net_forward_pass():
     net = model.Net()
-    test_tensor = torch.randn(3, 5)  # Batch of 3 samples with 5 features
+    test_tensor = torch.randn(3, 5)  # Batch of l3 samples with 5 features
     output = net(test_tensor)
     assert output.shape == torch.Size([3])  # Should return 1 prediction per sample
     assert (output >= 0).all() and (