egemenzeytinci

Send hex code
⌥←Delete = 0x17 - delete word
^←Delete = 0x15 - delete line

Send escape sequence
⌥← = Esc + b = move to left
⌥→ = Esc + f = move to right

egemenzeytinci

import matplotlib.pyplot as plt
import pandas as pd


def pie_by_first_n(df, label_col, size_col, other_name='others', n=5):
    df_sum = df.groupby(label_col)[size_col].sum().reset_index()
    df_sum = df_sum.sort_values(by=size_col, ascending=False)
    
    df2 = df_sum[:n].copy()
    

egemenzeytinci

import pandas as pd

# display full columns
pd.set_option('display.max_columns', None)  

# display full rows
pd.set_option('display.max_rows', None)

# non-truncated col values
pd.set_option('display.max_colwidth', -1)

egemenzeytinci

from oauth2client.service_account import ServiceAccountCredentials
import httplib2
import os

SCOPE = 'API_SCOPE'
ACCOUNT = 'SERVICE_ACCOUNT'
KEY = 'KEY_PATH'


def initialize():

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')

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

#!/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

cleaned = df.copy()

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

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

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'