Spaces:
Sleeping
Sleeping
File size: 6,613 Bytes
7e94977 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
import streamlit as st
import pickle
import numpy as np
import pandas as pd
# page configuration
st.set_page_config(
page_title="Diabetes Prediction App",
page_icon="🏥",
layout="centered"
)
# loading the model
@st.cache_resource
def load_model():
try:
with open('xgboost_model.pkl', 'rb') as file:
model = pickle.load(file)
return model
except Exception as e:
st.error(f"Error loading model: {str(e)}")
return None
def preprocess_input(gender, age, hypertension, heart_disease, smoking_history, bmi, hba1c_level, blood_glucose_level):
"""
Preprocess the input data (matching training data)
"""
data = {
'gender_Female': [0],
'gender_Male': [0],
'gender_Other': [0],
'smoking_history_No Info': [0],
'smoking_history_current': [0],
'smoking_history_ever': [0],
'smoking_history_former': [0],
'smoking_history_never': [0],
'smoking_history_not current': [0],
'age': [age],
'hypertension': [hypertension],
'heart_disease': [heart_disease],
'bmi': [bmi],
'HbA1c_level': [hba1c_level],
'blood_glucose_level': [blood_glucose_level]
}
# gender
gender_map = {0:'Female', 1:'Male'}
data[f'gender_{gender_map[gender]}'] = [1]
# smoking history
smoking_map = {
0: 'never',
1: 'former',
2: 'current',
3: 'not current',
4: 'ever',
5: 'No Info'
}
data[f'smoking_history_{smoking_map[smoking_history]}'] = [1]
# dataFrame
df = pd.DataFrame(data)
# Ensure exact column order as seen in the training data
expected_columns = [
'gender_Female', 'gender_Male', 'gender_Other',
'smoking_history_No Info', 'smoking_history_current',
'smoking_history_ever', 'smoking_history_former',
'smoking_history_never', 'smoking_history_not current', 'age',
'hypertension', 'heart_disease', 'bmi', 'HbA1c_level',
'blood_glucose_level'
]
df = df.reindex(columns=expected_columns,fill_value=0)
return df
def main():
st.title("Diabetes Prediction System 🏥")
st.markdown("""
This app predicts the likelihood of diabetes based on various health parameters.
Please fill in the information below to get a prediction.
""")
with st.form("prediction_form"):
st.subheader("Patient Information")
col1, col2 = st.columns(2)
with col1:
gender = st.selectbox(
"Gender",
options=[0, 1],
format_func=lambda x: "Female" if x == 0 else "Male"
)
age = st.number_input(
"Age",
min_value=0,
max_value=120,
value=40
)
hypertension = st.selectbox(
"Hypertension",
options=[0, 1],
format_func= lambda x: "No" if x == 0 else "Yes"
)
heart_disease = st.selectbox(
"Heart Disease",
options=[0, 1],
format_func= lambda x: "No" if x == 0 else "Yes"
)
with col2:
smoking_history = st.selectbox(
"Smoking History",
options=[0, 1, 2, 3, 4, 5],
format_func=lambda x: {
0: "Never",
1: "Former",
2: "Current",
3: "Not Current",
4: "Ever",
5: "No Info"
}[x]
)
bmi = st.number_input(
"BMI",
min_value=10.0,
max_value=100.0,
value=25.0,
step=0.1
)
hba1c_level = st.number_input(
"HbA1c Level",
min_value=3.0,
max_value=15.0,
value=5.5,
step=0.1
)
blood_glucose_level = st.number_input(
"Blood Glucose Level",
min_value=50,
max_value=500,
value=120
)
submit_button = st.form_submit_button("Predict")
model = load_model()
if submit_button and model is not None:
try:
# Preprocess the input data
input_df = preprocess_input(
gender, age, hypertension, heart_disease,
smoking_history, bmi, hba1c_level, blood_glucose_level
)
# Debug information
with st.expander("Show preprocessed features"):
st.write(input_df)
# Make prediction
prediction = model.predict(input_df)
probability = model.predict_proba(input_df)[0][1]
# Display results
st.subheader("Prediction Results")
col1, col2 = st.columns(2)
with col1:
if prediction[0] == 1:
st.error("High Risk of Diabetes")
else:
st.success("Low Risk of Diabetes")
with col2:
st.metric(
label="Risk Probability",
value=f"{probability:.1%}"
)
# Display input summary
st.subheader("Input Summary")
summary_df = pd.DataFrame({
'Feature': [
'Gender', 'Age', 'Hypertension', 'Heart Disease',
'Smoking History', 'BMI', 'HbA1c Level', 'Blood Glucose Level'
],
'Value': [
'Male' if gender == 1 else 'Female',
f"{age} years",
'Yes' if hypertension == 1 else 'No',
'Yes' if heart_disease == 1 else 'No',
{0: "Never", 1: "Former", 2: "Current", 3: "Not Current", 4: "Ever", 5: "No Info"}[smoking_history],
f"{bmi:.1f}",
f"{hba1c_level:.1f}",
f"{blood_glucose_level:.0f}"
]
})
st.dataframe(summary_df, hide_index=True)
except Exception as e:
st.error(f"Error making prediction: {str(e)}")
st.error("Please check the model compatibility with the input features.")
if __name__ == "__main__":
main() |