app.py

import pandas as pd
df=pd.read_excel("new_model_train_urine.xlsx")
from imblearn.over_sampling import SMOTE
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, MaxAbsScaler
from sklearn.neighbors import KNeighborsClassifier
import streamlit as st




X=df.iloc[:,:-1].values
y=df.iloc[:,-1].values
smote_object=SMOTE()
X_new,y_new=smote_object.fit_resample(X,y)


X_train,X_test,y_train,y_test=train_test_split(X_new,y_new,random_state=15)

sc=MaxAbsScaler()
X_train_new=sc.fit_transform(X_train)
X_test_new=sc.transform(X_test)

model=KNeighborsClassifier(n_neighbors=7,p=1)
model=model.fit(X_train_new,y_train)

st.title('Infection detection')
st.title(':blue[Urine test]:')
Age = st.number_input("Age",min_value=1, max_value=100)
options = ["Male", "Female"]
selectbox_selection = st.selectbox("Select Gender", options)
#st.write(f"Gender selected is {selectbox_selection}")
Fever = st.number_input("Fever",min_value=98, max_value=104)
options1 = ["Yes", "No"]
selectbox_selection = st.selectbox("Bone_merrow_transplantation", options1)
HB = st.number_input("HB",min_value=1, max_value=20)
platet = st.number_input("platet")
CRP= st.number_input("CRP")
Procalictonin =st.number_input("Procalictonin")
E_colli= st.number_input("E_colli")
Result1 =0
Klebsilla = st.number_input("Klebsilla")
Result2 = 0
Pseudomonas= st.number_input("Pseudomonas")
Result3 = 0
submit=st.button("Result")
gender = 1
Bone_merrow_transplantation=1

if float(E_colli)<= -10:
    Result1 = 1
if float(Klebsilla)<= -10:
    Result2 = 1
if float(Pseudomonas)<= -10:
    Result3 = 1
if selectbox_selection == "FEMALE":
    gender = 0
if selectbox_selection == "NO":
    Bone_merrow_transplantation=0


sapmle=[Age, gender, Fever, Bone_merrow_transplantation, HB, platet, CRP, Procalictonin, E_colli, Result1, Klebsilla, Result2, Pseudomonas, Result3]
s=model.predict([sapmle])
st.write(s)
print(s)