avisionh

import os
import json


def compare_files(file1_path, file2_path):
    """
    Compares two files line by line and identifies unique records in each.

    Args:
        file1_path (str): The path to the first file.

avisionh

# Secrets and credentials should be stored here as environmental variables. For example:
#
#   # Google Cloud authentication credentials
#   export GOOGLE_APPLICATION_CREDENTIALS="path/to/credentials.json"
#
# These environment variables can then be read in by Python using `os.getenv`:
#
#   --------------------------------------------------------
#   import os
#

avisionh

# https://stackoverflow.com/a/42260631/13416265
import pandas as pd
  
# create dataframe
df = pd.DataFrame(data={'INDICATOR': ['A', 'B', 'C', 'D'], 
                        'VALUE': [10, 9, 8, 7]})

# create translation dictionary
values_dict = {'A': 1, 'B': 2, 'C': 3, 'D': 4}

avisionh

Cypher style guide as advocated by Neo4j:

• Node labels are CamelCase and begin with an upper-case letter (examples: Person, NetworkAddress). Note that node labels are case-sensitive.
• Property keys, variables, parameters, aliases, and functions are camelCase and begin with a lower-case letter (examples: businessAddress, title). Note that these elements are case-sensitive.
• Relationship types are in upper-case and can use the underscore. (examples: ACTED_IN, FOLLOWS). Note that relationship types are case-sensitive and that you cannot use the “-” character in a relationship type.
• Cypher keywords are upper-case (examples: MATCH, RETURN). Note that Cypher keywords are case-insensitive, but a best practice is to use upper-case.
• String constants are in single quotes, unless the string contains a quote or apostrophe (examples: ‘The Matrix’, “Something’s Gotta Give”). Note that you can also escape single or double quotes within strings that are quoted with the same using a backslash character.

avisionh

// examine data model
CALL db.schema.visualization();

// return 6 movie nodes released after 2005
MATCH (film:Movie) 
WHERE film.released > 2005 
RETURN film 
LIMIT 6;

// count number of movies nodes released after 2005

avisionh

from multiprocessing import Pool
from functools import partial
from tqdm import tqdm

import pandas as pd

def parallelise_dataframe(df, func, n_cores=1, n_splits=1, **kwargs):
    """ Apply a function on a dataframe in parallel
    reference: https://towardsdatascience.com/make-your-own-super-pandas-using-multiproc-1c04f41944a1#6028
    reference: https://stackoverflow.com/questions/34031681/passing-kwargs-with-multiprocessing-pool-map

avisionh

We couldn’t find that file to show.

avisionh

from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
import numpy as np

# create data
cities = ['London', 'Shanghai', 'Seoul', 'Seoul', 'London']

n_rows = len(cities)

# represent/encode these categories as integers

avisionh

# doesn't work because have 2FA
# https://pygithub.readthedocs.io/en/latest/introduction.html
# https://pygithub.readthedocs.io/en/latest/examples/Repository.html#get-a-specific-content-file
from github import Github

# create Github instance
password = os.getenv("GITHUB_PASSWORD")
g = Github("avisionh", password)

repo = g.get_repo("lukes/ISO-3166-Countries-with-Regional-Codes")

avisionh

import pandas as pd
import requests

# get country lookups
url = "https://unstats.un.org/unsd/methodology/m49/"
html = requests.get(url).content
data_countries = pd.read_html(html)
 # take first list element which is in English
data_countries = data_countries[0]