app.py

import streamlit as st
import pandas as pd
import pickle

import numpy as np
import pandas as pd
import seaborn as sns
from sklearn.pipeline import Pipeline
from sklearn.pipeline import make_pipeline

from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import IsolationForest
from sklearn.tree import DecisionTreeClassifier

from fs import FeatureSelection

from xgboost import XGBClassifier

import warnings
warnings.filterwarnings('ignore')
from sklearn import set_config
set_config(display="diagram")


    

with open('mejor_modelo_tp4.pkl', 'rb') as f:
    modelo = pickle.load(f)


# Define una función para hacer predicciones con el modelo
def predecir(features):
    # Procesa los valores de features y hace predicciones con el modelo
    predicciones = modelo.predict(features)
    return predicciones

# 'Unnamed: 0', 'acc_max', 'gyro_max', 'acc_kurtosis', 'gyro_kurtosis',
#        'label', 'lin_max', 'acc_skewness', 'gyro_skewness', 'post_gyro_max',
#        'post_lin_max', 'fall']

# Crea la aplicación Streamlit
def app():
    
    st.title('Ingrese los valores de las features')

    col1, col2, col3 = st.columns(3)

    with col1:
            feature1 = st.text_input('Unnamed: 0', value = 61)

    with col2:
            feature2 = st.text_input('acc_max', value = 26.310655)

    with col3:
            feature3 = st.text_input('gyro_max', value = 5.192876)

    col4, col5, col6 = st.columns(3)

    with col4:
            feature4 = st.text_input('acc_kurtosis', value = 17.569042)

    with col5:
            feature5 = st.text_input('gyro_kurtosis', value = 9.776727)

    with col6:
            feature6 = st.text_input('label', value = 'FOL')
    
    col7, col8, col9 = st.columns(3)

    with col7:
            feature7 = st.text_input('lin_max', value = 11.584056)

    with col8:
            feature8 = st.text_input('acc_skewness', value = 3.587634)

    with col9:
            feature9 = st.text_input('gyro_skewness', value = 2.848477)

    col10, col11, col12 = st.columns(3)

    with col10:
            feature10 = st.text_input('post_gyro_max', value = 4.691588)

    with col11:
            feature11 = st.text_input('post_lin_max', value = 10.684285)

    # with col12:
    #         feature12 =  st.text_input('3')
    # # # Crea los campos de entrada de texto para las features
    # feature1 = st.text_input('Unnamed: 0')
    # feature2 = st.text_input('acc_max')
    # feature3 = st.text_input('gyro_max')
    # feature4 = st.text_input('acc_kurtosis')
    # feature5 = st.text_input('gyro_kurtosis')
    # feature6 = st.text_input('label')
    # feature7 = st.text_input('lin_max')
    # feature8 = st.text_input('acc_skewness')
    # feature9 = st.text_input('gyro_skewness')
    # feature10 = st.text_input('post_gyro_max')
    # feature11 = st.text_input('post_lin_max')

    # Crea un botón para hacer predicciones con el modelo
    if st.button('Predecir'):
        # Convierte los valores de features en un DataFrame de Pandas
        features = pd.DataFrame({
            'Unnamed: 0': [feature1],
            'acc_max': [feature2],
            'gyro_max': [feature3],
            'acc_kurtosis': [feature4],
            'gyro_kurtosis': [feature5],
            'label': [feature6],
            'lin_max': [feature7],
            'acc_skewness': [feature8],
            'gyro_skewness': [feature9],
            'post_gyro_max': [feature10],
            'post_lin_max': [feature11],          
        })
        
        # if predecir(features) == 0:
        #     predicciones = 'NO '
        # else:
        #     predicciones = ''
        if predecir(features) == [0]:
               respuesta = ' NO  '
        else:
               respuesta = ' SI  '
        st.write(f'Estos datos {respuesta}son compatibles con una caída')

    if st.button('Modelo'):
               
        st.write(modelo.named_steps)

# Ejecuta la aplicación Streamlit
if __name__ == '__main__':
    app()