ipeirotis

import argparse
import csv
import json
import os
import re
import sys
import time
from dataclasses import asdict, is_dataclass
from datetime import datetime, timezone
from typing import Any, Dict, List, Optional, Tuple

ipeirotis

import json
import os
import re
import time
from tqdm import tqdm
from dataclasses import dataclass
from datetime import datetime
from typing import Any, Dict, List, Optional, Tuple

import pandas as pd

ipeirotis

import json
import os
from getpass import getpass
from pathlib import Path
from typing import Dict, List, Optional, Union

from IPython.display import display, HTML, JSON


try:

ipeirotis

  SELECT 
    P1.*
    , COALESCE(P1.count-P2.count,P1.count) AS count_without_missing
    , P2.count AS count_missing
  FROM 
    itemsets P1 
    JOIN itemsets P2  ON (P1.email = P2.email) 
  WHERE 
    P2.itemset_size>=2 AND 
    P1.itemset_size = P2.itemset_size - 1  AND 

ipeirotis

# We use the "CUBE" operator, to calculate the frequency of any 
# attribute-value combination.
#
# Notice that we replace the NULL values with "N/A" before the CUBE operator. 
# This is to avoid confusion with the way that CUBE uses NULL values to indicate 
# "any value" for attribute combinations that do not use the available attributes 
# of the cube. 

df = (
  dataset

ipeirotis

ipeirotis

# Long version with full comments

# We want to plot the distribution of salaries in baseball leagues over time

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt

# Download a dataset from Lahman's database of baseball statistics 

ipeirotis

# Panos Ipeirotis, Oct 30 2016
# Just trying to keep my 5yo busy while it is pouring rain outside...

import random
import emoji # https://pypi.python.org/pypi/emoji/

# Selection from http://www.webpagefx.com/tools/emoji-cheat-sheet/
emojis = [':apple:', ':green_apple:', ':tangerine:', ':lemon:', ':cherries:', ':grapes:', ':watermelon:', ':strawberry:',
':peach:', ':melon:', ':banana:', ':pear:', ':pineapple:', ':sweet_potato:', ':eggplant:', ':tomato:', ':corn:']

ipeirotis

ipeirotis

### Cohort Analysis

import matplotlib.pyplot as plt

# Connect to the BigQuery API
from googleapiclient.discovery import build
from oauth2client import client
credentials = client._get_application_default_credential_from_file('client_secrets.json')
credentials = credentials.create_scoped('https://www.googleapis.com/auth/bigquery')