Ricardo Rosas rrosasl

💭

Working on Data Science Nanodegree - Udacity

World traveler. Business Analytics. Python and VBA/Excel.

rrosasl / Sankey.py

Created November 25, 2020 18:05

SankeyDiagram


	def genSankey(df,cat_cols=[],value_cols='',title='Sankey Diagram'):

	'''
	https://gist.github.com/ken333135/09f8793fff5a6df28558b17e516f91ab
	'''
	# maximum of 6 value cols -> 6 colors
	colorPalette = ['#4B8BBE','#306998','#FFE873','#FFD43B','#646464']
	labelList = []
	colorNumList = []

rrosasl / selecting_winner.py

Created November 25, 2020 17:58

Selecting winner

	left_voters = []
	losers = []
	for r in range(1,df.shape[1]-1):
	#Stop loop when there are already two candidates
	if vote_rounds[r-1].nunique() == 2:
	break

	#Start the new voting round
	vote_rounds[r] = vote_rounds[r-1]

rrosasl / first_round.py

Created November 25, 2020 17:19

FIrst round of voting

	#Create Data Frame where results will be stored
	results = []
	vote_rounds = pd.DataFrame()

	df_t = df.transpose() # Change rows and columns to have voters as columns
	for col in df_t.columns:
	top_choice = df_t[col].min() #Choose their Top Canidate
	top_candidate = df_t[df_t[col] == top_choice].index.tolist()[0]
	results.append(top_candidate)

rrosasl / cleaning_g_sheet.py

Created November 25, 2020 17:10

Cleaning spreadsheet data

	# Convert Rows into DataFrame and clean data
	new_header = df.iloc[0] #grab the first row for the header
	df = df[1:] #take the data less the header row
	df.columns = new_header #set the header row as the df header
	df = df.iloc[:,1:] # Remove time stamp

	# Convert to a DataFrame and render.
	df = pd.DataFrame.from_records(rows)

	new_header = df.iloc[0] #grab the first row for the header

rrosasl / importing_g_sheet.py

Last active November 25, 2020 17:11

Importing google sheet

	auth.authenticate_user()
	# https://colab.research.google.com/notebooks/snippets/sheets.ipynb
	import gspread
	from oauth2client.client import GoogleCredentials
	gc = gspread.authorize(GoogleCredentials.get_application_default())
	#worksheet = gc.open('Your spreadsheet name').sheet1
	wb = gc.open_by_url('https://docs.google.com/spreadsheets/d/1cH8SE6ba4LqYA0kIS8n9LFt2zJQvh7EZaldcJ_MzgyA/edit#gid=48937339')
	# get_all_values gives a list of rows.
	wb = wb.worksheet('Form Responses 1')
	rows = wb.get_all_values()