pemagrg1

import numpy as np
docs = "Can I eat the Pizza".lower().split()
doc1 = set(docs)
doc1 = sorted(doc1)
print ("\nvalues: ", doc1)

integer_encoded = []
for i in docs:
    v = np.where( np.array(doc1) == i)[0][0]
    integer_encoded.append(v)

pemagrg1

from numpy import array
from numpy import argmax
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
# define example
# data = ['cold', 'cold', 'warm', 'cold', 'hot', 'hot', 'warm', 'cold', 'warm', 'hot']


doc1 = "Can I eat the Pizza".lower()
doc2 = "You can eat the Pizza".lower()

pemagrg1

from keras.preprocessing.text import Tokenizer
from numpy import array
from numpy import argmax
from keras.utils import to_categorical


doc = "Can I eat the Pizza".lower().split()

def using_Tokenizer(doc):
    # create the tokenizer

pemagrg1

import tensorflow as tf
import pandas as pd

text = 'My cat is a great cat'
tokens = text.lower().split()

vocab = set(tokens)
vocab = pd.Series(range(len(vocab)), index=vocab)

word_ids = vocab.loc[tokens].values

pemagrg1

"""
Get total of each column values
"""
def totalcount(data):
    return data.assign(Total=data.drop('Total', errors='ignore', axis=1).sum(1))

def pandas_get_total_row(df):
  df = df.pipe(totalcount).T.pipe(totalcount).T
  return df

pemagrg1

def get_total(df):
    df.loc['Total'] = pd.Series(df['Marks'].sum(), index = ['Marks'])
    return df

df = pd.DataFrame({'Subjects': ["Maths","Science","English"], 'Marks': [80,90,75]})
df = df.reindex(columns=['Subjects','Marks'])
df = get_total(df)
df

pemagrg1

from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd
from sklearn import svm
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import pickle
from sklearn import linear_model
Project_path = "<path to the project folder>"

pemagrg1

import pickle

Project_path = "<path to project>"
model_path = Project_path + "/08. Multi-class_text_classification/models/model.pickle"
vectorizer_path = Project_path + "/08. Multi-class_text_classification/models/vectorizer.pickle"

vectorizer = pickle.load(open(vectorizer_path,'rb'))
model = pickle.load(open(model_path,'rb'))
pred = model.predict(vectorizer.transform(["i have got a new phone. its from Apple.. and i love it!"]))[0]
print ("predicted class:", pred)

pemagrg1

"""
regex based to search if a page is inner page or home page or category page.
"""
import re


def url_check(url):
    url = url.split("/")
    url = list(filter(None, url))
    if "http" in url[0]:

pemagrg1

"""
In audio production, a sample rate (or "sampling rate") defines how many times per second a sound is sampled. 
Technically speaking, it is the frequency of samples used in a digital recording.
"""
import numpy as np
from scipy.io import wavfile

sampleRate = 100
frequency = 10
audio_length = 1 #second