databyjp’s gists

databyjp / further_annotations_20220215_test_analyse_gamelogs.py

Created February 17, 2022 06:30

	fig.add_shape(type="rect",
	x0=rtg_min, y0=rtg_mid, x1=rtg_mid, y1=rtg_max,
	fillcolor="LightSeaGreen",
	opacity=0.25,
	line_width=0,
	layer="below"
	)
	fig.add_shape(type="rect",
	x0=rtg_mid, y0=rtg_min, x1=rtg_max, y1=rtg_mid,
	fillcolor="LightSteelBlue",

databyjp / updated_plot_20220215_test_analyse_gamelogs.py

Last active February 17, 2022 05:18

	fig = px.scatter(df, x="DEF_RATING", y="OFF_RATING",
	color="legend",
	title=f"Game-by-game performances by the {highlight_tm} - '21-'22",
	color_discrete_sequence=["#eeeeee", color_dict[highlight_tm][0], color_dict[highlight_tm][1]],
	size="inv_days_since_game",
	size_max=18,
	template="plotly_white",
	width=1200, height=800,
	labels={"OFF_RATING": "Offensive Rating (higher is better)",
	"DEF_RATING": "Dffensive Rating (to the left is better)",

databyjp / updated_plot_20220215_test_analyse_gamelogs.py

Created February 17, 2022 05:02

	thresh_days = 20
	df = df.assign(legend="Other teams")
	df.loc[df["TEAM_NAME"] == highlight_tm, "legend"] = f"{thresh_days}+ days ago"
	df.loc[(df.days_since_game < thresh_days) & (df["TEAM_NAME"] == highlight_tm), "legend"] = f"In the last {thresh_days} days"

	fig = px.scatter(df, x="DEF_RATING", y="OFF_RATING",
	color="legend",
	title=f"Game-by-game performances by the {highlight_tm} - '21-'22",
	color_discrete_sequence=["#dddddd", color_dict[highlight_tm][0], color_dict[highlight_tm][1]],
	size="inv_days_since_game",

databyjp / preproc_20220215_test_analyse_gamelogs.py

Created February 16, 2022 14:58

	import logging
	import pandas as pd
	import plotly.express as px
	import json
	import os
	import utils

	logger = logging.getLogger(__name__)
	root_logger = logging.getLogger()
	root_logger.setLevel(logging.INFO)

databyjp / update_box_score - update_data.py

Created February 16, 2022 14:20

	def update_box_scores(box_json_dir="dl_data/box_scores/json"):
	"""
	Download all box scores from NBA API
	:param box_json_dir: Directory to save downloads to
	:return:
	"""
	logger.info("Starting download of game box scores...")
	gldf = utils.load_gamelogs()
	gldf = gldf.sort_values("gamedate_dt")
	gm_ids = gldf["Game_ID"].unique()

databyjp / fetch_box_score - update_data.py

Created February 16, 2022 14:19

	def fetch_box_score(json_dir, gm_id):
	"""
	Download one box score from NBA API
	:param json_dir: Directory for saving downloaded JSON
	:param gm_id: NBA game ID
	:return:
	"""
	from nba_api.stats.endpoints import boxscoreadvancedv2
	dl_path = os.path.join(json_dir, gm_id + ".json")
	if os.path.exists(dl_path):

databyjp / example_player_boxscore

Created February 16, 2022 14:09

	GAME_ID TEAM_ID TEAM_ABBREVIATION TEAM_CITY PLAYER_ID PLAYER_NAME NICKNAME START_POSITION COMMENT MIN ... TM_TOV_PCT EFG_PCT TS_PCT USG_PCT E_USG_PCT E_PACE PACE PACE_PER40 POSS PIE
	0 0022100860 1610612760 OKC Oklahoma City 1629647 Darius Bazley Darius F 39:34 ... 0.0 0.529 0.573 0.213 0.215 105.83 104.33 86.94 85 0.115
	1 0022100860 1610612760 OKC Oklahoma City 1630598 Aaron Wiggins Aaron F 33:50 ... 0.0 0.200 0.200 0.059 0.064 103.94 107.12 89.27 76 0.025
	2 0022100860 1610612760 OKC Oklahoma City 1629676 Isaiah Roby Isaiah C 22:03 ... 0.0 0.500 0.436 0.132 0.132 101.01 97.96 81.63 46 0.020
	3 0022100860 1610612760 OKC Oklahoma C

databyjp / example_team_boxscore

Created February 16, 2022 14:07


	GAME_ID TEAM_ID TEAM_NAME TEAM_ABBREVIATION TEAM_CITY MIN E_OFF_RATING OFF_RATING E_DEF_RATING DEF_RATING ... TM_TOV_PCT EFG_PCT TS_PCT USG_PCT E_USG_PCT E_PACE PACE PACE_PER40 POSS PIE
	0 0022100860 1610612760 Thunder OKC Oklahoma City 265:00 114.5 116.5 109.2 110.8 ... 10.1 0.568 0.589 1.0 0.202 101.23 99.62 83.02 109 0.531
	1 0022100860 1610612752 Knicks NYK New York 265:00 109.2 110.8 114.5 116.5 ... 12.6 0.486 0.523 1.0 0.197 101.23 99.62 83.02 111 0.469
	[2 rows x 29 columns]

databyjp / asset_correlation_get_variance.py

Created March 29, 2021 04:22

	temp_syms = [s for s in list(sp500_df[sp500_df.Sector == sect].Symbol.values) if s in df.symbol.unique()]
	temp_syms = random.sample(temp_syms, n_symbols)
	pf1_df = df[df.symbol.isin(temp_syms)]
	pf1_avg = get_avg_prices(pf1_df)
	pf1_var = pf1_avg.var()

databyjp / asset_correlation_build_sim_matrix.py

Created March 20, 2021 15:46

	# ========== DETERMINE SIMILARITIES ==========
	# Calculate similarities between each stock
	r_array = np.zeros([len(symbols), len(symbols)])
	p_array = np.zeros([len(symbols), len(symbols)])
	for i in range(len(symbols)):
	for j in range(len(symbols)):
	vals_i = df[df["symbol"] == symbols[i]]['close'].values
	vals_j = df[df["symbol"] == symbols[j]]['close'].values
	r_ij, p_ij = scipy.stats.pearsonr(vals_i, vals_j)
	r_array[i, j] = r_ij

JP Hwang databyjp