Spaces:
Runtime error
Runtime error
File size: 2,878 Bytes
9596562 2a9d346 9596562 aad3f84 9596562 aad3f84 9596562 aad3f84 9596562 aad3f84 9596562 aad3f84 9596562 aad3f84 0db9e5f aad3f84 0db9e5f aad3f84 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | import pytest
import pandas as pd
import numpy as np
import os
import sys
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../backend')))
from preprocessing import preprocess_data, resolve_model_dir
def test_resolve_model_dir():
md = resolve_model_dir()
assert md.endswith("model")
def test_preprocess_data_training(tmp_path):
df = pd.DataFrame({
'Heart Rate (bpm)': [80, 90, np.nan],
'SpO2 Level (%)': [98, 97, 95],
'Systolic Blood Pressure (mmHg)': [120, 125, 130],
'Diastolic Blood Pressure (mmHg)': [80, 85, 90],
'Body Temperature (°C)': [37.0, 37.2, 37.5],
'Predicted Disease': ['Normal', 'Asthma', 'Normal']
})
# Use tmp_path to isolate test artifacts from production models
X, y = preprocess_data(df, is_training=True, model_dir=str(tmp_path))
assert not X.isnull().values.any()
assert len(y) == 3
assert 'Risk_Severity' in X.columns
assert os.path.exists(os.path.join(str(tmp_path), 'label_encoder.pkl'))
def test_preprocess_data_inference(tmp_path):
# First fit on dummy data inside tmp_path
train_df = pd.DataFrame({
'Heart Rate (bpm)': [80, 90],
'SpO2 Level (%)': [98, 97],
'Systolic Blood Pressure (mmHg)': [120, 125],
'Diastolic Blood Pressure (mmHg)': [80, 85],
'Body Temperature (°C)': [37.0, 37.2],
'Predicted Disease': ['Normal', 'Asthma']
})
preprocess_data(train_df, is_training=True, model_dir=str(tmp_path))
df = pd.DataFrame({
'Heart Rate (bpm)': [100],
'SpO2 Level (%)': [99],
'Systolic Blood Pressure (mmHg)': [120],
'Diastolic Blood Pressure (mmHg)': [80],
'Body Temperature (°C)': [37.0],
})
X, y = preprocess_data(df, is_training=False, model_dir=str(tmp_path))
assert y is None
assert 'Risk_Severity' in X.columns
def test_preprocess_data_alias_normalization(tmp_path):
"""Test that schema field names (e.g. Heart_Rate) are automatically normalized without error."""
# First fit on dummy data inside tmp_path
train_df = pd.DataFrame({
'Heart Rate (bpm)': [80, 90],
'SpO2 Level (%)': [98, 97],
'Systolic Blood Pressure (mmHg)': [120, 125],
'Diastolic Blood Pressure (mmHg)': [80, 85],
'Body Temperature (°C)': [37.0, 37.2],
'Predicted Disease': ['Normal', 'Asthma']
})
preprocess_data(train_df, is_training=True, model_dir=str(tmp_path))
df = pd.DataFrame({
'Heart_Rate': [115],
'SpO2_Level': [92],
'Systolic_BP': [145],
'Diastolic_BP': [92],
'Body_Temp': [37.4],
})
X, y = preprocess_data(df, is_training=False, model_dir=str(tmp_path))
assert 'Risk_Severity' in X.columns
assert 'Heart Rate (bpm)' in X.columns
assert not X.isnull().values.any()
|