Keep Getting This Error

Traceback (most recent call last): File "C:/Users/davis/AppData/Local/Programs/Python/Python36-32/SeniorProject.py", line 13, in dataset["HomeWin"] = dataset["VisitorPts"] < dataset["HomePts"] File "C:\Users\davis\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\ops.py", line 837, in wrapper return self._constructor(na_op(self.values, other.values), File "C:\Users\davis\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\ops.py", line 792, in na_op raise TypeError("invalid type comparison") TypeError: invalid type comparison

Code

import pandas as pd import numpy as np

dataset = pd.read_csv("seniorproject.csv", parse_dates=[1], skiprows=[0,]) print(dataset) dataset.columns = ["Visitor Team","VisitorPts","Home Team","HomePts","Score Type","Team","Rk","Home Team Win"] #dataset.columns = ["Visitor Team", "VisitorPts", "Home Team", "HomePts"]

dataset.ix[:5]

dataset["HomeWin"] = dataset["VisitorPts"] < dataset["HomePts"] y_true = dataset["HomeWin"].values

from collections import defaultdict

won_last = defaultdict(int)

dict_variable = {}

for index, row in dataset.iterrows(): # remove two print lines below if you don't need them # I have included them to show the output on terminal #print(index) #print(row) home_team = row["Home Team"] visitor_team = row["Visitor Team"] row["HomeLastWin"] = won_last[home_team] row["VisitorLastWin"] = won_last[visitor_team] dataset.ix[index] = row won_last[home_team] = row["HomeWin"] won_last[visitor_team] = not row["HomeWin"] dataset["Home Last Win"] = False dataset["Visitor Last Win"] = False from collections import defaultdict won_last = defaultdict(int) for index, row in dataset.iterrows(): home_team = row["Home Team"] visitor_team = row["Visitor Team"] row["Home Last Win"] = won_last[home_team] row["Visitor Last Win"] = won_last[visitor_team] dataset.ix[index] = row #We then set our dictionary with the each team's result (from this row) for the next #time we see these teams. #Set current Win won_last[home_team] = row["Home Team Win"] won_last[visitor_team] = not row["Home Team Win"]

dataset["Home Win Streak"] = 0 dataset["Visitor Win Streak"] = 0 win_streak = defaultdict(int)

for index, row in dataset.iterrows(): home_team = row["Home Team"] visitor_team = row["Visitor Team"] row["Home Win Streak"] = win_streak[home_team] row["Visitor Win Streak"] = win_streak[visitor_team] dataset.ix[index] = row # Set current win if row["Home Team Win"]: win_streak[home_team] += 1 win_streak[visitor_team] = 0 else: win_streak[home_team] = 0 win_streak[visitor_team] += 1

dataset["Home Team Ranks Higher"] = 0 for index , row in dataset.iterrows(): home_team = row["Home Team"] visitor_team = row["Visitor Team"] home_rank = dataset[dataset["Team"] == home_team]["Rk"].values visitor_rank = dataset[dataset["Team"] == visitor_team]["Rk"].values row["Home Team Rank Higher"] = (home_rank > visitor_rank) dataset.ix[index] = row

last_match_winner = defaultdict(int) dataset["Home Team Won Last"] = 0 for index , row in dataset.iterrows(): home_team = row["Home Team"] visitor_team = row["Visitor Team"] teams = tuple(sorted([home_team, visitor_team])) row["Home Team Won Last"] = 1 if last_match_winner[teams] == row["Home Team"] else 0 dataset.ix[index] = row # Who won this one? winner = row["Home Team"] if row["Home Team Win"] else row["Visitor Team"] last_match_winner[teams] = winner X_features_only = dataset[['Home Win Streak', 'Visitor Win Streak', 'Home Team Ranks Higher', 'Home Team Won Last', 'Home Last Win', 'Visitor Last Win']].values

import numpy as np from sklearn.tree import DecisionTreeClassifier clf = DecisionTreeClassifier(random_state=14) from sklearn.model_selection import cross_val_score

scores = cross_val_score(clf, X_features_only, y_true, scoring='accuracy') print(scores) print("Using just the last result from the home and visitor teams") print("Accuracy: {0:.1f}%".format(np.mean(scores) * 100))