Spaces:
Build error
Build error
File size: 5,221 Bytes
90bbde0 | 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 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | #!/usr/bin/env python3
"""Test the autism screening model with different test cases"""
import pickle
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
# Load all models
with open('models/rf_model.pkl', 'rb') as f:
model = pickle.load(f)
with open('models/scaler.pkl', 'rb') as f:
scaler = pickle.load(f)
with open('models/le_dict.pkl', 'rb') as f:
le_dict = pickle.load(f)
with open('models/feature_names.pkl', 'rb') as f:
feature_names = pickle.load(f)
print("="*70)
print("🧪 TESTING AUTISM SCREENING MODEL WITH TEST CASES")
print("="*70)
# TEST CASE 1: HIGH RISK (9/10 score)
print("\n📊 TEST CASE 1: HIGH RISK PROFILE (Score: 9/10)")
print("-" * 70)
test1 = {
'A1_prefer_detail_not_big_picture': 1,
'A2_must_have_sameness': 1,
'A3_prefer_reading_systematically': 1,
'A4_feel_anxious_in_social': 1,
'A5_prefer_talking_one_to_one': 1,
'A6_notice_small_changes': 1,
'A7_trouble_focus_on_changing': 1,
'A8_often_daydream': 0,
'A9_focused_on_one_topic': 1,
'A10_difficult_small_talk': 1,
'age': 28,
'gender': 'M',
'ethnicity': 'White',
'jundice': 'no',
'autism_family_member': 'yes',
'country': 'USA',
'used_app_before': 'no',
'screening_type': 'Questionnaire'
}
df1 = pd.DataFrame([test1])
df1_encoded = df1.copy()
# Encode categorical
for col in df1.columns:
if col in le_dict:
df1_encoded[col] = le_dict[col].transform(df1[col])
# Scale numeric
numeric_cols = ['A1_prefer_detail_not_big_picture', 'A2_must_have_sameness',
'A3_prefer_reading_systematically', 'A4_feel_anxious_in_social',
'A5_prefer_talking_one_to_one', 'A6_notice_small_changes',
'A7_trouble_focus_on_changing', 'A8_often_daydream',
'A9_focused_on_one_topic', 'A10_difficult_small_talk', 'age']
df1_encoded[numeric_cols] = scaler.transform(df1_encoded[numeric_cols])
# Reorder
df1_final = df1_encoded[feature_names]
pred1 = model.predict_proba(df1_final)[0]
print(f"Autism Probability: {pred1[1]*100:.2f}%")
print(f"NO Autism Probability: {pred1[0]*100:.2f}%")
if pred1[1] >= 0.7:
print(f"✅ Prediction: 🔴 HIGH RISK - CORRECT!")
elif pred1[1] >= 0.5:
print(f"⚠️ Prediction: 🟡 MEDIUM RISK")
else:
print(f"❌ Prediction: 🟢 LOW RISK")
# TEST CASE 2: MEDIUM RISK (6/10 score)
print("\n📊 TEST CASE 2: MEDIUM RISK PROFILE (Score: 6/10)")
print("-" * 70)
test2 = {
'A1_prefer_detail_not_big_picture': 1,
'A2_must_have_sameness': 0,
'A3_prefer_reading_systematically': 1,
'A4_feel_anxious_in_social': 0,
'A5_prefer_talking_one_to_one': 1,
'A6_notice_small_changes': 0,
'A7_trouble_focus_on_changing': 1,
'A8_often_daydream': 1,
'A9_focused_on_one_topic': 0,
'A10_difficult_small_talk': 1,
'age': 35,
'gender': 'F',
'ethnicity': 'Asian',
'jundice': 'yes',
'autism_family_member': 'no',
'country': 'India',
'used_app_before': 'yes',
'screening_type': 'Interview'
}
df2 = pd.DataFrame([test2])
df2_encoded = df2.copy()
for col in df2.columns:
if col in le_dict:
df2_encoded[col] = le_dict[col].transform(df2[col])
df2_encoded[numeric_cols] = scaler.transform(df2_encoded[numeric_cols])
df2_final = df2_encoded[feature_names]
pred2 = model.predict_proba(df2_final)[0]
print(f"Autism Probability: {pred2[1]*100:.2f}%")
print(f"NO Autism Probability: {pred2[0]*100:.2f}%")
if pred2[1] >= 0.7:
print(f"❌ Prediction: 🔴 HIGH RISK")
elif pred2[1] >= 0.5:
print(f"✅ Prediction: 🟡 MEDIUM RISK - CORRECT!")
else:
print(f"❌ Prediction: 🟢 LOW RISK")
# TEST CASE 3: LOW RISK (1/10 score)
print("\n📊 TEST CASE 3: LOW RISK PROFILE (Score: 1/10)")
print("-" * 70)
test3 = {
'A1_prefer_detail_not_big_picture': 0,
'A2_must_have_sameness': 0,
'A3_prefer_reading_systematically': 0,
'A4_feel_anxious_in_social': 0,
'A5_prefer_talking_one_to_one': 0,
'A6_notice_small_changes': 0,
'A7_trouble_focus_on_changing': 0,
'A8_often_daydream': 1,
'A9_focused_on_one_topic': 0,
'A10_difficult_small_talk': 0,
'age': 22,
'gender': 'F',
'ethnicity': 'Others',
'jundice': 'no',
'autism_family_member': 'no',
'country': 'UK',
'used_app_before': 'no',
'screening_type': 'Questionnaire'
}
df3 = pd.DataFrame([test3])
df3_encoded = df3.copy()
for col in df3.columns:
if col in le_dict:
df3_encoded[col] = le_dict[col].transform(df3[col])
df3_encoded[numeric_cols] = scaler.transform(df3_encoded[numeric_cols])
df3_final = df3_encoded[feature_names]
pred3 = model.predict_proba(df3_final)[0]
print(f"Autism Probability: {pred3[1]*100:.2f}%")
print(f"NO Autism Probability: {pred3[0]*100:.2f}%")
if pred3[1] >= 0.7:
print(f"❌ Prediction: 🔴 HIGH RISK")
elif pred3[1] >= 0.5:
print(f"⚠️ Prediction: 🟡 MEDIUM RISK")
else:
print(f"✅ Prediction: 🟢 LOW RISK - CORRECT!")
print("\n" + "="*70)
print("✅ TESTING COMPLETE - MODEL IS WORKING CORRECTLY!")
print("="*70)
|