RKHS_SHAP_preprocess.py

import shap
import pandas as pd
import os
import numpy as np
if __name__ == '__main__':
    X,y = shap.datasets.adult()
    print(X.columns)
    X = X.values
    y = np.where(np.array(y)*1.0==0,-1,1)
    if not os.path.exists('census'):
        os.makedirs('census')
    fn='census'
    with open(f'{fn}/X.npy', 'wb') as f:
        np.save(f, X)
    with open(f'{fn}/y.npy', 'wb') as f:
        np.save(f, y)

##############


    prefix = "archive/"
    matches = pd.read_csv(prefix+"matches.csv")
    participants = pd.read_csv(prefix+"participants.csv")
    stats1 = pd.read_csv(prefix+"stats1.csv", low_memory=False)
    stats2 = pd.read_csv(prefix+"stats2.csv", low_memory=False)
    stats = pd.concat([stats1,stats2])

    # merge into a single DataFrame
    a = pd.merge(participants, matches, left_on="matchid", right_on="id")
    allstats_orig = pd.merge(a, stats, left_on="matchid", right_on="id")
    allstats = allstats_orig.copy()

    # drop games that lasted less than 10 minutes
    allstats = allstats.loc[allstats["duration"] >= 10*60,:]

    # Convert string-based categories to numeric values
    cat_cols = ["role", "position", "version", "platformid"]
    for c in cat_cols:
        allstats[c] = allstats[c].astype('category')
        allstats[c] = allstats[c].cat.codes
    allstats["wardsbought"] = allstats["wardsbought"].astype(np.int32)

    X = allstats.drop(["win"], axis=1)
    y = allstats["win"]

    # convert all features we want to consider as rates
    rate_features = [
        "kills", "deaths", "assists", "killingsprees", "doublekills",
        "triplekills", "quadrakills", "pentakills", "legendarykills",
        "totdmgdealt", "magicdmgdealt", "physicaldmgdealt", "truedmgdealt",
        "totdmgtochamp", "magicdmgtochamp", "physdmgtochamp", "truedmgtochamp",
        "totheal", "totunitshealed", "dmgtoobj", "timecc", "totdmgtaken",
        "magicdmgtaken" , "physdmgtaken", "truedmgtaken", "goldearned", "goldspent",
        "totminionskilled", "neutralminionskilled", "ownjunglekills",
        "enemyjunglekills", "totcctimedealt", "pinksbought", "wardsbought",
        "wardsplaced", "wardskilled"
    ]
    for feature_name in rate_features:
        X[feature_name] /= X["duration"] / 60 # per minute rate

    # convert to fraction of game
    X["longesttimespentliving"] /= X["duration"]

    # define friendly names for the features
    full_names = {
        "kills": "Kills per min.",
        "deaths": "Deaths per min.",
        "assists": "Assists per min.",
        "killingsprees": "Killing sprees per min.",
        "longesttimespentliving": "Longest time living as % of game",
        "doublekills": "Double kills per min.",
        "triplekills": "Triple kills per min.",
        "quadrakills": "Quadra kills per min.",
        "pentakills": "Penta kills per min.",
        "legendarykills": "Legendary kills per min.",
        "totdmgdealt": "Total damage dealt per min.",
        "magicdmgdealt": "Magic damage dealt per min.",
        "physicaldmgdealt": "Physical damage dealt per min.",
        "truedmgdealt": "True damage dealt per min.",
        "totdmgtochamp": "Total damage to champions per min.",
        "magicdmgtochamp": "Magic damage to champions per min.",
        "physdmgtochamp": "Physical damage to champions per min.",
        "truedmgtochamp": "True damage to champions per min.",
        "totheal": "Total healing per min.",
        "totunitshealed": "Total units healed per min.",
        "dmgtoobj": "Damage to objects per min.",
        "timecc": "Time spent with crown control per min.",
        "totdmgtaken": "Total damage taken per min.",
        "magicdmgtaken": "Magic damage taken per min.",
        "physdmgtaken": "Physical damage taken per min.",
        "truedmgtaken": "True damage taken per min.",
        "goldearned": "Gold earned per min.",
        "goldspent": "Gold spent per min.",
        "totminionskilled": "Total minions killed per min.",
        "neutralminionskilled": "Neutral minions killed per min.",
        "ownjunglekills": "Own jungle kills per min.",
        "enemyjunglekills": "Enemy jungle kills per min.",
        "totcctimedealt": "Total crown control time dealt per min.",
        "pinksbought": "Pink wards bought per min.",
        "wardsbought": "Wards bought per min.",
        "wardsplaced": "Wards placed per min.",
        "turretkills": "# of turret kills",
        "inhibkills": "# of inhibitor kills",
        "dmgtoturrets": "Damage to turrets"
    }
    feature_names = [full_names.get(n, n) for n in X.columns]
    print(feature_names)
    X.columns = feature_names
    X = X.values
    y = y.values
    y = np.where(np.array(y)*1.0==0,-1,1)

    if not os.path.exists('LOL'):
        os.makedirs('LOL')
    fn='LOL'
    with open(f'{fn}/X.npy', 'wb') as f:
        np.save(f, X)
    with open(f'{fn}/y.npy', 'wb') as f:
        np.save(f, y)