Spaces:
Runtime error
Runtime error
rajababu15
commited on
Commit
•
f62a6e1
1
Parent(s):
d808041
created app.py
Browse files
app.py
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import pickle
|
4 |
+
|
5 |
+
# Load the preprocessor and model from the pickle files
|
6 |
+
with open('preprocesor.pkl', 'rb') as file:
|
7 |
+
preprocessor = pickle.load(file)
|
8 |
+
|
9 |
+
with open('model.pkl', 'rb') as file:
|
10 |
+
model = pickle.load(file)
|
11 |
+
|
12 |
+
# Define the app
|
13 |
+
def run():
|
14 |
+
st.title("Model Testing App")
|
15 |
+
|
16 |
+
# Create inputs for all features
|
17 |
+
Timestamp = st.date_input("Timestamp")
|
18 |
+
Age = st.number_input("Age", min_value=0, max_value=100)
|
19 |
+
Gender = st.selectbox("Gender", ["Male", "Female", "M"])
|
20 |
+
Country = st.text_input("Country")
|
21 |
+
state = st.text_input("State")
|
22 |
+
self_employed = st.checkbox("Self Employed")
|
23 |
+
family_history = st.checkbox("Family History")
|
24 |
+
treatment = st.selectbox("Treatment", ["Yes", "No"])
|
25 |
+
work_interfere = st.selectbox("Work Interfere", ["Sometimes", "Never", "Often"])
|
26 |
+
no_employees = st.selectbox("No. of Employees", ["1-5", "6-25", "26-100", "100-500", "500-1000", "More than 1000"])
|
27 |
+
remote_work = st.checkbox("Remote Work")
|
28 |
+
tech_company = st.checkbox("Tech Company")
|
29 |
+
benefits = st.selectbox("Benefits", ["Yes", "No", "Don't know"])
|
30 |
+
care_options = st.selectbox("Care Options", ["Yes", "No", "Not sure"])
|
31 |
+
wellness_program = st.selectbox("Wellness Program", ["Yes", "No", "Don't know"])
|
32 |
+
seek_help = st.selectbox("Seek Help", ["Yes", "No", "Don't know"])
|
33 |
+
anonymity = st.selectbox("Anonymity", ["Yes", "No", "Don't know"])
|
34 |
+
leave = st.selectbox("Leave", ["Somewhat easy","Somewhat difficult","Very difficult","Don't know"])
|
35 |
+
mental_health_consequence = st.selectbox("Mental Health Consequence", ["Yes","No","Maybe"])
|
36 |
+
phys_health_consequence = st.selectbox("Physical Health Consequence", ["Yes","No","Maybe"])
|
37 |
+
coworkers = st.selectbox("Coworkers", ["Yes","No","Some of them"])
|
38 |
+
supervisor = st.selectbox("Supervisor", ["Yes","No","Some of them"])
|
39 |
+
mental_health_interview = st.selectbox("Mental Health Interview", ["Yes","No","Maybe"])
|
40 |
+
phys_health_interview = st.selectbox("Physical Health Interview", ["Yes","No","Maybe"])
|
41 |
+
mental_vs_physical = st.selectbox("Mental vs Physical", ["Yes","No","Don't know"])
|
42 |
+
obs_consequence = st.selectbox("Obs Consequence", ["Yes","No"])
|
43 |
+
|
44 |
+
# Create a new data point
|
45 |
+
new_data = pd.DataFrame({
|
46 |
+
"Timestamp": [Timestamp],
|
47 |
+
"Age": [Age],
|
48 |
+
"Gender": [Gender],
|
49 |
+
"Country": [Country],
|
50 |
+
"state": [state],
|
51 |
+
"self_employed": [self_employed],
|
52 |
+
"family_history": [family_history],
|
53 |
+
"treatment": [treatment],
|
54 |
+
"work_interfere": [work_interfere],
|
55 |
+
"no_employees": [no_employees],
|
56 |
+
"remote_work": [remote_work],
|
57 |
+
"tech_company": [tech_company],
|
58 |
+
"benefits": [benefits],
|
59 |
+
"care_options": [care_options],
|
60 |
+
"wellness_program": [wellness_program],
|
61 |
+
"seek_help": [seek_help],
|
62 |
+
"anonymity": [anonymity],
|
63 |
+
"leave": [leave],
|
64 |
+
"mental_health_consequence": [mental_health_consequence],
|
65 |
+
"phys_health_consequence": [phys_health_consequence],
|
66 |
+
"coworkers": [coworkers],
|
67 |
+
"supervisor": [supervisor],
|
68 |
+
"mental_health_interview": [mental_health_interview],
|
69 |
+
"phys_health_interview": [phys_health_interview],
|
70 |
+
"mental_vs_physical": [mental_vs_physical],
|
71 |
+
"obs_consequence": [obs_consequence]
|
72 |
+
})
|
73 |
+
|
74 |
+
# Preprocess the new data
|
75 |
+
new_data_transformed = preprocessor.transform(new_data.drop(columns=['treatment'],axis=1))
|
76 |
+
|
77 |
+
# Make a prediction
|
78 |
+
prediction = model.predict(new_data_transformed)[0]
|
79 |
+
|
80 |
+
if st.button('Predict'):
|
81 |
+
if prediction == 1:
|
82 |
+
result ='Yes'
|
83 |
+
st.success('The output is {}'.format(result))
|
84 |
+
else:
|
85 |
+
result ='No'
|
86 |
+
st.success('The output is {}'.format(result))
|
87 |
+
|
88 |
+
if __name__=='__main__':
|
89 |
+
run()
|