import streamlit as st

st.markdown("# Abuse Detection")

st.sidebar.markdown(" #Abuse Detection")

import pandas as pd

import os

import pickle

import librosa

import numpy as np

import pandas as pd

import seaborn as sns

import soundfile as sf

from sklearn.svm import SVC

import matplotlib.pyplot as plt

from sklearn import preprocessing

from sklearn.model_selection import train_test_split

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

def extract_features(x, path):

x.append(feature)

def LabelEncoder(arr, le):

return Y

Y = np.array(['No' 'Yes' 'Yes' 'No' 'Yes' 'Yes' 'Yes' 'Yes' 'Yes' 'Yes' 'No' 'No' 'Yes'

'Yes' 'No' 'No' 'No' 'No'])

le = preprocessing.LabelEncoder()

Y = LabelEncoder(Y, le)

Y = np.array(['No' 'Yes'])

model = pickle.load(open('SVC_Model_abuse.sav', 'rb'))

X = []

path = "/home/gaurav/Desktop/music-genre-classification-using-machine-learning-main/Abuse_0.wav"

extract_features(X, path)

y_pre = model.predict(X)

if(y_pre==1):

print("Abuse Detected")

else:

print("No Abuse")

#le.inverse_transform(y_pre)