Solution

from sklearn.cluster import KMeans
import pandas as pd
def group(n):
    df = pd.DataFrame.from_csv("RegressionMatrix1.csv",encoding="UTF-8")
    SP500 = pd.DataFrame.from_csv("SP500.csv", encoding="UTF-8")
    df = df.fillna(0)
    tickers = []
    for x in SP500["Ticker"].values:
        if "." in x:
            x = x.replace(".","")
        tickers.append(x)
    SP500["Ticker"]=tickers
    SP500.index = SP500["Ticker"]


    df = df.transpose()

    zScores = pd.DataFrame()
    for x in df.columns:
        zScores[x] = (df[x] - df[x].mean())/df[x].std(ddof=0)

    SP500 = pd.concat([SP500,df],axis=1,join="inner")

    model = KMeans(n_clusters=n)
    model = model.fit(zScores)
    SP500["Group"] = model.labels_
    return SP500

SP500 = group(8)
print(SP500.groupby("Group")["GICS Sector"].value_counts())

You will notice that there is going to be a difference, but this is normal for machine learning. You won’t get the same results each time because of the way this works, but you can expect to get similar results.

Source Code