DFoly

from typing import List, Dict, Tuple

x: int = 10
y: float = 0.8
string: str = 'I am a string'
hash_map: Dict[str, int] = {}
List1: List[int] = []
my_tuple: Tuple[str, int] = ()
    

DFoly

import numpy as np
import pandas as pd
from sklearn.datasets import make_blobs
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression


class CustomImputer(BaseEstimator, TransformerMixin):

DFoly

import numpy as np
import pandas as pd
from typing import Dict, List
from sklearn.datasets import make_blobs
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression

DFoly

      def _e_step(self, X, pi, mu, sigma):
        """Performs E-step on GMM model

        Parameters:
        ------------
        X: (N x d), data points, m: no of features
        pi: (C), weights of mixture components
        mu: (C x d), mixture component means
        sigma: (C x d x d), mixture component covariance matrices

DFoly

from apache_beam.options.pipeline_options import PipelineOptions
from google.cloud import pubsub_v1
from google.cloud import bigquery
import apache_beam as beam
import logging
import argparse
import sys
import re

DFoly

import mysql.connector 
from mysql.connector import Error
import os
import re
import pandas as pd 
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import nltk
from wordcloud import WordCloud, STOPWORDS

DFoly

class GMM:
    """ Gaussian Mixture Model
    
    Parameters
    -----------
        k: int , number of gaussian distributions
        
        seed: int, will be randomly set if None
        
        max_iter: int, number of iterations to run algorithm, default: 200

DFoly

class GMM:
    """ Gaussian Mixture Model
    
    Parameters
    -----------
        k: int , number of gaussian distributions
        
        seed: int, will be randomly set if None
        
        max_iter: int, number of iterations to run algorithm, default: 200

DFoly

import mysql.connector
from mysql.connector import Error
import tweepy
import json
from dateutil import parser
import time
import os
import subprocess

#importing file which sets env variable

DFoly

import mysql.connector 
from mysql.connector import Error
import os
import re
import pandas as pd 
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
from nltk.stem import WordNetLemmatizer
import nltk