databyjp’s gists

databyjp / nba_travel_impact_get_data.py

Last active February 26, 2020 02:57

	# Get all team totals for all dates
	temp_df_list = list()
	for game_date in game_dates:
	logger.info(f'Getting data for games on {game_date}')
	temp_boxes = client.team_box_scores(day=game_date.day, month=game_date.month, year=game_date.year)
	temp_df = pd.DataFrame(temp_boxes)
	temp_df = temp_df.assign(game_date=str(game_date))
	temp_df_list.append(temp_df)

	# ========== SET UP BOX SCORE DATAFRAME ==========

databyjp / nba_travel_impact_counts

Created February 26, 2020 04:23

	>>> travel_cats = ['home', 'travelled', 'rest_cats']
	... travel_grp_df = box_df.groupby(travel_cats).sum()
	... travel_grp_df = travel_grp_df.assign(games=box_df.groupby(travel_cats)['minutes_played'].count())
	... travel_grp_df.reset_index(drop=False, inplace=True)
	... print(travel_grp_df[travel_cats + ['games']])
	home travelled rest_cats games
	0 False False 2+ Days 15
	1 False True 0 Days 246
	2 False True 1 Days 717
	3 False True 2+ Days 252

databyjp / nba_travel_impact_treemap.py

Last active February 26, 2020 06:06

	# TREEMAPS
	travel_cats = ['home', 'travelled', 'rest_cats']
	travel_grp_df = box_df.groupby(travel_cats).sum()
	travel_grp_df = travel_grp_df.assign(games=box_df.groupby(travel_cats)['minutes_played'].count())
	travel_grp_df.reset_index(drop=False, inplace=True)

	chart_cats = ['home_str', 'travelled_str', 'rest_cats']
	home_away = pd.Series(['Home ' * i for i in travel_grp_df.home.values]) + pd.Series(['Away ' * (1-i) for i in travel_grp_df.home.values])
	travel_grp_df['home_str'] = home_away
	travelled = pd.Series(['Travelled ' * i for i in travel_grp_df.travelled.values]) + pd.Series(['Stayed ' * (1-i) for i in travel_grp_df.travelled.values])

databyjp / dash_simple_nba_data_head

Created February 29, 2020 09:55

	>>> all_teams_df.head()
	player pl_acc pl_pps min_start min_mid min_end shots_count shots_made shots_freq shots_acc group
	0 Jahlil Okafor 65.1 132.6 1 0.5 1 3 1 3.7 33.3 NOP
	1 Jaxson Hayes 77.8 155.6 1 0.5 1 3 2 3.7 66.7 NOP
	2 Nicolo Melli 36.4 88.6 1 0.5 1 1 1 1.2 100.0 NOP
	3 Zion Williamson 54.3 111.4 1 0.5 1 2 1 2.5 50.0 NOP
	4 Frank Jackson 44.7 105.3 1 0.5 1 0 0 0.0 0.0 NOP

databyjp / dash_simple_nba_local_plot_pretty.py

Created February 29, 2020 10:37

	def clean_chart_format(fig):
	import plotly.graph_objects as go
	fig.update_layout(
	paper_bgcolor="white",
	plot_bgcolor="white",
	annotations=[
	go.layout.Annotation(
	x=0.9,
	y=1.02,
	showarrow=False,

databyjp / dash_simple_nba_simple_app.py

Created February 29, 2020 10:56

	import pandas as pd
	import dash
	import dash_core_components as dcc
	import dash_html_components as html
	from dash.dependencies import Input, Output

	all_teams_df = pd.read_csv('srcdata/shot_dist_compiled_data_2019_20.csv')

	app = dash.Dash(__name__)
	server = app.server

databyjp / dash_simple_nba_app_w_format.py

Last active February 1, 2021 17:31

databyjp / nba_storytime_datahead

Created March 6, 2020 04:00

	>>> records_df.head()
	date team conference net_score games wins losses
	0 2018-10-16 PHILADELPHIA_76ERS Eastern -18 1 0 1
	1 2018-10-16 BOSTON_CELTICS Eastern 18 1 1 0
	2 2018-10-16 OKLAHOMA_CITY_THUNDER Western -8 1 0 1
	3 2018-10-16 GOLDEN_STATE_WARRIORS Western 8 1 1 0
	4 2018-10-17 MILWAUKEE_BUCKS Eastern 1 1 1 0

databyjp / sixdegs_leagues_set_initdata.py

Created March 14, 2020 04:22

	# Calculate data
	utc = pytz.UTC
	filt_sch_data = nba_sch_data[nba_sch_data.datetime > utc.localize(pd.to_datetime(seed_date))]

	teams_contacted_df.loc[teams_contacted_df.team == seed_tm, 'contacted'] = True
	teams_contacted_df.loc[teams_contacted_df.team == seed_tm, 'con_from'] = seed_tm
	teams_contacted_df.loc[teams_contacted_df.team == seed_tm, 'date'] = pd.to_datetime(seed_date).date()
	teams_contacted_df.loc[teams_contacted_df.team == seed_tm, 'deg_sep'] = 0

databyjp / sixdegs_leagues_iterate_data.py

Last active March 14, 2020 04:29

	# Iterate every row of schedule:
	for temp_tup in filt_sch_data.itertuples():
	home_tm_contacted = teams_contacted_df.loc[teams_contacted_df.team == temp_tup.home_team, 'contacted']
	away_tm_contacted = teams_contacted_df.loc[teams_contacted_df.team == temp_tup.away_team, 'contacted']
	if home_tm_contacted.values[0] != away_tm_contacted.values[0]:

	home_away = [temp_tup.home_team, temp_tup.away_team]
	for i in range(len(home_away)):
	tm = home_away[i]
	other_tm = home_away[1-i]

JP Hwang databyjp