maxwellbade

def timeline_plot(df,x_axis,y_axis,index_col,title,height,width,template):
    
    #dummy column for yaxis
    def even_odd(row):
        if row[index_col] % 2 == 0:
            return 1
        else:
            return -1
    df[y_axis] = df.apply(lambda row: even_odd(row), axis = 1)
    

maxwellbade

def experiment_forecast(df,date_col,experiment_name
                        ,metric_name,variant_name
                        ,steps,title):
    
    import statsmodels.api as sm

    #get dates and metric
    df = df
    df_dau = df[df['experiment_name'] == experiment_name]
    df_dau = df_dau[df_dau['metric_name'] == metric_name]

maxwellbade

start_time = datetime.now()
print('Start Time: ', start_time)

import bs4
import requests
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import time
import pandas as pd

maxwellbade

import requests
import re
import json
import pandas as pd

import warnings
warnings.filterwarnings('ignore')

city = 'austin/' #*****change this city to what you want!!!!*****

maxwellbade

import requests
import re
import json
import time

import warnings
warnings.filterwarnings('ignore')

city = 'austin/' #*****change this city to what you want!!!!*****

maxwellbade

import requests
import re
import json

import warnings
warnings.filterwarnings('ignore')

url='https://www.zillow.com/homes/for_sale/2_p/?searchQueryState=%7B%22pagination%22%3A%7B%22currentPage%22%3A2%7D%2C%22mapBounds%22%3A%7B%22west%22%3A-97.88981437683105%2C%22east%22%3A-97.78407096862793%2C%22south%22%3A30.136145838104586%2C%22north%22%3A30.208863801102932%7D%2C%22isMapVisible%22%3Atrue%2C%22filterState%22%3A%7B%22sort%22%3A%7B%22value%22%3A%22days%22%7D%2C%22ah%22%3A%7B%22value%22%3Atrue%7D%7D%2C%22isListVisible%22%3Atrue%2C%22mapZoom%22%3A13%7D'

data = json.loads(re.search(r'!--(\{"queryState".*?)-->', r.text).group(1))

maxwellbade

#single attributes
new_rules['softblocked'] = new_rules['softblocked'].astype(float)
new_rules = new_rules.sort_values(by='softblocked',ascending=True)

fig = px.scatter(new_rules
            ,x='softblocked_rate'
            ,y='softblocked'
            ,color='groupcols'
            ,log_y=True
            ,template='plotly_dark'

maxwellbade

start_time = datetime.now()
print('Start Time: ', start_time)

cols = [
        'avg_posts_per_day'
        ,'max_posts_per_day_bucket'
        ,'days_since_registered_bucket'
        ,'shortest_time_bt_posts_seconds_bucket'
        ,'count_users_per_ip_bucket'
        ,'count_dmas_bucket'

maxwellbade

#do not insert columns with null values
def fraud_rate(df, agg, cols=None, threshold=None, limit=None, days=None, minrate=None, maxrate=None):
    if isinstance(cols, str):
        groupcols = [cols]
    elif cols is None:
        groupcols = [] 
    else:
        try:
            groupcols = list(cols)
        except:

maxwellbade

from fuzzywuzzy import process, fuzz

def fuzzy(col, risky_words, score):
    fuzzy_words, score = process.extractOne(col, risky_words, scorer=score)
    if score<85:
        return 'no_high_matches'
    else:
        return fuzzy_words,score

start_time = datetime.now()