preproc_20220215_test_analyse_gamelogs.py

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)
sh = logging.StreamHandler()
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
sh.setFormatter(formatter)
root_logger.addHandler(sh)

desired_width = 320
pd.set_option('display.max_columns', 20)
pd.set_option('display.width', desired_width)

json_dir = "dl_data/box_scores/json"
json_files = [i for i in os.listdir(json_dir) if i.endswith("json")]


def box_json_to_df(content, data="team"):
    if data == "team":
        sel_int = 1
    elif data == "player":
        sel_int = 0
    else:
        logger.warning("")

    results = content["resultSets"][sel_int]
    headers = results["headers"]
    rows = results["rowSet"]
    df = pd.DataFrame(rows)
    df.columns = headers
    return df


df_list = list()
for json_file in json_files:
    json_path = os.path.join(json_dir, json_file)
    with open(json_path, 'r') as f:
        content = json.load(f)
    tdf = box_json_to_df(content, data="team")
    df_list.append(tdf)
df = pd.concat(df_list)
df = df[df["GAME_ID"].str[:5] == "00221"]

gldf = utils.load_gamelogs()
df = pd.merge(
    df,
    gldf[["Game_ID", "gamedate_dt"]],
    left_on="GAME_ID",
    right_on="Game_ID",
    how="left",
)