egemenzeytinci

# three quantiles to rfm values
df['r_val'] = pd.qcut(df['recency'], q=3, labels=range(3, 0, -1))
df['f_val'] = pd.qcut(df['frequency'], q=3, labels=range(1, 4))
df['m_val'] = pd.qcut(df['monetary'], q=3, labels=range(1, 4))

# create the segment value
df['rfm_val'] = (
    df['r_val'].astype(str) + 
    df['f_val'].astype(str) + 
    df['m_val'].astype(str)

egemenzeytinci

from py2neo import Graph
import pandas as pd

host = 'localhost'
port = 7687
user = ''
password = ''

graph = Graph(
    host=host,

egemenzeytinci

egemenzeytinci

class Report:
    def __init__(self, X_test, y_test):
        self.X = X_test
        self.y = y_test
    
    def metrics(self, model):
        y_pred = model.predict(self.X)
        
        print('Accuracy score:\n')
        print(accuracy_score(self.y, y_pred))

egemenzeytinci

def compare():
    for is_le in [True, False]:
        method = 'label encoder'
        
        if is_le:
            selected = df_le[selects_le + ['is_canceled']]
        else:
            selected = df_hot[selects_hot + ['is_canceled']]
            method = 'dummy variables'
        

egemenzeytinci

def select(X):
    selects = []
    
    selector = SelectKBest(chi2, k='all').fit(X, y)
    scores = selector.scores_
        
    q3 = np.quantile(scores, 0.75)
    q1 = np.quantile(scores, 0.25)
    iqr = q3 - q1
    threshold = q3 + 1.5 * iqr

egemenzeytinci

cleaned = df.copy()

columns = [
    'lead_time',
    'stays_in_weekend_nights',
    'stays_in_week_nights',
    'adults',
    'children',
    'babies',
    'adr',

egemenzeytinci

#!/usr/bin/env python
# encoding: utf-8

import tweepy #https://github.com/tweepy/tweepy
import csv

#Twitter API credentials
consumer_key = ""
consumer_secret = ""
access_key = ""

egemenzeytinci

from rfpimp import permutation_importances
from sklearn.base import clone
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split
import pandas as pd


def imp_df(column_names, importances):
    data = {

egemenzeytinci

from nltk.corpus import stopwords
from stemming.porter2 import stem
import nltk
import re
import string

nltk.download('punkt')
nltk.download('stopwords')
default_stopwords = stopwords.words('english')