makispl

def make_predictions():
    """
    Returns a dataframe with the predicted clusters.
    Parameters
    ---------
    -
    Returns
    -------
    preds_df : a dataframe object
             Contains the per game 'pred_cluster'

makispl

# import the libraries
from nba_api.stats.endpoints import boxscoreadvancedv2
import sqlite3 as sql
import pandas as pd
import numpy as np
from multiprocessing import Pool
import requests
from functools import partial
from io import BytesIO
import os

makispl

makispl

if __name__ == "__main__":

    # load the full training data with folds
    df = pd.read_csv('../data/processed/train_proc_labeled_folds.csv',
                     converters={'GAME_ID': lambda x: str(x)})

    features = [
      'DEF_RATING',
      'AST_PCT',
      'AST_RATIO',

makispl

makispl

def feat_permutation_importance(df, feats, model):
    """
    Takes in a dataframe of 'plays', features list
    and model, plots and returns the mean score across
    all the folds
    Parameters
    ---------
    df : a dataframe object
            Contains the plays
    feats : a list object

makispl

def run_model(df, folds, feats, model):
    """
    Takes in a dataframe of 'plays', the # folds,
    features list and model, prints and returns
    the mean score across all the folds
    Parameters
    ---------
    df : a dataframe object
            Contains the plays
    folds : int

makispl

# read in the training data
plays_df = pd.read_csv('../data/interim/plays_17_18_19_pre_proc_train.csv',
                       converters={'GAME_ID': lambda x: str(x)})

# switch to the for-normalisation-features
data_stnd = data.copy()

# instantiate, fit, transform scaler
scaler = MinMaxScaler()
data_stnd = scaler.fit_transform(data_stnd)

makispl

# allocate weights
wts = []

for col in features:
    if col in group_1:
        wts.append(0.5)
    elif col in group_2:
        wts.append(0.3)
    elif col in group_3:
        wts.append(0.2)

makispl