databyjp’s gists

databyjp / draw_map.py

Last active November 2, 2020 06:15

	# Map showing counties with typical income < 40k
	tmp_df = data_df[data_df["Median_Household_Income_2018"] < 40000]
	fig = px.choropleth_mapbox(tmp_df, locations="fips", color="Median_Household_Income_2018",
	range_color=[0, 100000],
	geojson=counties, color_continuous_scale=px.colors.diverging.RdYlBu, labels=labels)
	fig.update_layout(coloraxis_colorbar=dict(
	tickvals=[0, 20000, 40000, 60000, 80000, 100000],
	ticktext=["0", "20k", "40k", "60k", "80k", "100k+"]
	))
	fig.update_layout(mapbox_style="carto-positron",

databyjp / draw_map.py

Last active November 2, 2020 06:14

	fig = px.choropleth_mapbox(data_df, locations="fips", color="Median_Household_Income_2018",
	range_color=[0, 100000],
	geojson=counties, color_continuous_scale=px.colors.diverging.RdYlBu, labels=labels)
	fig.update_layout(coloraxis_colorbar=dict(
	tickvals=[0, 20000, 40000, 60000, 80000, 100000],
	ticktext=["0", "20k", "40k", "60k", "80k", "100k+"]
	))
	fig.update_layout(mapbox_style="carto-positron",
	mapbox_zoom=3.9, mapbox_center={"lat": 37.0902, "lon": -95.7129},
	margin={"r": 0, "t": 0, "l": 0, "b": 0})

databyjp / data_predict_bpm_everything.py

Created September 18, 2020 14:48

	import pandas as pd
	import numpy as np
	import plotly.express as px
	import streamlit as st
	from sklearn import model_selection
	from sklearn import preprocessing
	from sklearn import linear_model
	from sklearn import svm
	from sklearn import metrics

databyjp / data_predict_bpm_preproc.py

Last active September 18, 2020 14:46

	import pandas as pd
	import numpy as np
	import plotly.express as px
	import streamlit as st
	from sklearn import model_selection
	from sklearn import preprocessing
	from sklearn import linear_model
	from sklearn import svm
	from sklearn import metrics

databyjp / scraper_mult_pages.py

Created August 26, 2020 12:10


	import pandas as pd

	# ===== START SCRAPING =====
	import requests
	from bs4 import BeautifulSoup
	import re


	def scrape_this(uri="/pages/forms/"):

databyjp / scraper_basic_get_table.py

Created August 26, 2020 11:41

	data_rows = table.find_all("tr", attrs={"class": "team"}) # Includes the header row!
	parsed_data = list()
	stat_keys = [col.attrs["class"][0] for col in data_rows[0].find_all("td")]

	for row in data_rows:
	tmp_data = dict()
	for attr in stat_keys:
	attr_val = row.find(attrs={"class": attr}).text
	tmp_data[attr] = re.sub(r"^\s+\|\s+$", "", attr_val)
	parsed_data.append(tmp_data)

databyjp / scraper_basic_element.py

Last active August 26, 2020 11:26

databyjp / scraper_nba_mult_pages_output.py

Created August 23, 2020 09:22

	>>> per_poss_df
	name g mp ... pts link season
	0 Sacramento Kings 82 20080 ... 105.6 /teams/SAC/2001.html 2001
	1 Milwaukee Bucks 82 19780 ... 108.8 /teams/MIL/2001.html 2001
	2 Los Angeles Lakers 82 19905 ... 108.4 /teams/LAL/2001.html 2001
	3 Dallas Mavericks 82 19805 ... 107.1 /teams/DAL/2001.html 2001
	4 Toronto Raptors 82 19955 ... 105.9 /teams/TOR/2001.html 2001
	.. ... .. ... ... ... ... ...
	25 New York Knicks 66 15965 ... 106.5 /teams/NYK/2020.html 2020
	26 Cleveland Cavaliers 65 15725 ... 107.5 /teams/CLE/2020.html 2020

databyjp / scraper_nba_mult_pages.py

Created August 23, 2020 09:19

	# ========== (c) JP Hwang 22/8/20 ==========

	import logging

	# ===== START LOGGER =====
	logger = logging.getLogger(__name__)
	root_logger = logging.getLogger()
	root_logger.setLevel(logging.INFO)
	sh = logging.StreamHandler()
	formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')

databyjp / scraper_nba_sample_output.py

Created August 23, 2020 08:49

	>>> per_gm_df
	name g mp ... pf pts link
	0 Dallas Mavericks 75 242.3 ... 19.5 117.0 /teams/DAL/2020.html
	1 Milwaukee Bucks 73 241.0 ... 19.6 118.7 /teams/MIL/2020.html
	2 Portland Trail Blazers 74 241.0 ... 21.7 115.0 /teams/POR/2020.html
	3 Houston Rockets 72 241.4 ... 21.8 117.8 /teams/HOU/2020.html
	4 Los Angeles Clippers 72 241.4 ... 22.1 116.3 /teams/LAC/2020.html
	5 New Orleans Pelicans 72 242.1 ... 21.2 115.8 /teams/NOP/2020.html
	6 Phoenix Suns 73 241.0 ... 22.0 113.6 /teams/PHO/2020.html
	7 Washington Wizards 72 241.0 ... 22.7 114.4 /teams/WAS/2020.html

JP Hwang databyjp