import pickle
import pandas as pd
import sklearn
import numpy as np
import gradio as gr
import imblearn
from app_function import *
import tensorflow as tf
from tensorflow.keras.applications import imagenet_utils
from tensorflow.keras.utils import img_to_array
from tensorflow.keras.models import load_model
import pdfplumber
import re
from collections import namedtuple
from compress_pickle import dump, load
demo = gr.Blocks(theme="peach")
with demo:
gr.Markdown(
"""
# Machine learning DEMO 🐠
---
""")
with gr.Tabs():
with gr.TabItem("Détéction d'une tumeur"):
my_input = gr.inputs.Image(shape=(224,224))
vgg16_button = gr.Button("Soumettre")
output_html = gr.outputs.HTML(label="")
# my_output = gr.Label(label="Resultat de la prédiction",num_top_classes=2)
with gr.TabItem("(PDF) Diabétique, prédiabétique ou sain"):
# POUR DIABETES FICHIER PDF
with gr.Row():
input_file_PDF = gr.File(label='PDF')
PDF_diabete_button = gr.Button("Soumettre")
df_ouput = gr.Dataframe(label="Caractéristique du patient",
headers=["HighBP","HighChol", "CholCheck", "BMI", "Smoker","Stroke","HeartDiseaseorAttack","PhysActivity","Fruits","Veggies","HvyAlcoholConsump","AnyHealthcare", "NoDocbcCost", "GenHlth","MentHlth", "PhysHlth", "DiffWalk","Sex", "Age", "Education","Income"],
row_count=1,col_count=(21),max_rows=2,overflow_row_behaviour='paginate')
output_html1 = gr.outputs.HTML(label="")
# text_output2 = gr.Label(label="Resultat de prédiction",num_top_classes=3)
with gr.TabItem("Public- Diabétique, prédiabétique ou sain"):
# POUR Diabetes
with gr.Row():
with gr.Group():
HighBP = gr.Radio(["Oui","Non"],type="index",label="HighBP")
HighChol = gr.Radio(["Oui","Non"],type="index",label="HighChol")
CholCheck = gr.Radio(["Oui","Non"],type="index",label="CholCheck")
with gr.Group():
Smoker = gr.Radio(["Oui","Non"],type="index",label="Smoker")
Stroke = gr.Radio(["Oui","Non"],type="index",label="Stroke")
HeartDiseaseorAttack = gr.Radio(["Oui","Non"],type="index",label="HeartDiseaseorAttack")
with gr.Group():
PhysActivity = gr.Radio(["Oui","Non"],type="index",label="PhysActivity")
Fruits = gr.Radio(["Oui","Non"],type="index",label="Fruits")
Veggies = gr.Radio(["Oui","Non"],type="index",label="Veggies")
with gr.Group():
HvyAlcoholConsump = gr.Radio(["Oui","Non"],type="index",label="HvyAlcoholConsump")
AnyHealthcare = gr.Radio(["Oui","Non"],type="index",label="AnyHealthcare")
NoDocbcCost = gr.Radio(["Oui","Non"],type="index",label="NoDocbcCost")
with gr.Row():
with gr.Group():
DiffWalk = gr.Radio(["Oui","Non"],type="index",label="DiffWalk")
Sex = gr.Dropdown(["femme","homme"],type="index",label="Sex")
with gr.Group():
BMI = gr.Slider(12, 98,value=70,label="BMI",step=1)
GenHlth = gr.Slider(1, 5,value=2,label="GenHlth",step=1)
MentHlth = gr.Slider(0, 30,value=20,label="MentHlth",step=1)
with gr.Group():
PhysHlth = gr.Slider(0, 30,value=14,label="PhysHlth",step=1)
Age = gr.Slider(1, 13,value=7,label="Age",step=1)
with gr.Group():
Education = gr.Slider(1, 6,value=4,label="Education",step=1)
Income = gr.Slider(1, 8,value=6,label="Income",step=1)
# text_output = gr.Label(num_top_classes=3)
Public_diabete_button = gr.Button("Soumettre")
input_data = [HighBP,HighChol, CholCheck, BMI, Smoker,Stroke,HeartDiseaseorAttack,
PhysActivity, Fruits, Veggies,HvyAlcoholConsump,AnyHealthcare, NoDocbcCost, GenHlth,
MentHlth, PhysHlth, DiffWalk,
Sex, Age, Education,Income]
output_html2 = gr.outputs.HTML(label="")
vgg16_button.click(Prediction_VGG16, inputs =my_input,outputs = [output_html])
PDF_diabete_button.click(get_data_inputPDF, inputs=input_file_PDF,outputs=[df_ouput,output_html1])
Public_diabete_button.click(user_input, inputs=input_data,outputs=[output_html2])
gr.Markdown(
"""