I am getting an error printed in my log. This algo did work but things became deprecated and I tried to update it but cannot figure out what I am doing wrong. The error is as follows:

The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().

from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC, NuSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn import preprocessing
from collections import Counter
import numpy as np

def initialize(context):

context.stocks = symbols('XLY',  # XLY Consumer Discrectionary SPDR Fund  
                       'XLF',  # XLF Financial SPDR Fund  
                       'XLK',  # XLK Technology SPDR Fund  
                       'XLE',  # XLE Energy SPDR Fund  
                       'XLV',  # XLV Health Care SPRD Fund  
                       'XLI',  # XLI Industrial SPDR Fund  
                       'XLP',  # XLP Consumer Staples SPDR Fund  
                       'XLB',  # XLB Materials SPDR Fund  
                       'XLU')  # XLU Utilities SPRD Fund  

context.historical_bars = 100     #recalls last 100 bars  
context.feature_window = 10    #slices of 10 day windows for each slice training occurs. if price goes up buy if price goes down sell  

def handle_data(context, data):
#prices = history(bar_count = context.historical_bars, frequency ='1d', field='price') "deprecated"
prices = data.history(context.stocks, 'price', context.historical_bars, frequency = '1d')
#todays price and 99 before is stored in pandas data frame of prices.

for stock in context.stocks:  
    try:  
        #ma1 = data[stock].mavg(50)    "deprecated"  
        price_hist = data.history(context.stocks, 'price', bar_count=50, frequency='1d')  
        ma1 = price_hist.mean()  

       # ma2 = data[stock].mavg(200)  "depricated"  
        price_hist = data.history(context.stocks, 'price', bar_count=200, frequency='1d')  
        ma2 = price_hist.mean()


        start_bar = context.feature_window        #has to start at 10 to get last 9 points.  
        price_list = prices[stock].tolist()       #column in pandas dataframe is converted to list

        X = []  #features           #is empty list that is populated by the last 10 days of prices  
        y = []  #labels  
 #feature sets^

        bar = start_bar  
        #feature creation  
        while bar < len(price_list)-1:                #lists start at 0 not 1  
            try:  
                end_price = price_list[bar+1]  
                begin_price = price_list[bar]  
                #says that the last price in the list is what wer'e interested in.  
                #was the subsequent price a rise or fall ex. [1,2,3,4,5,6,7,8,9,10,???]

                pricing_list = []    #actual list of prices  
                xx = 0                #counts us through  
                for _ in range(context.feature_window):  
                    price = price_list[bar-(context.feature_window-xx)]  
                    #take current bar were on and starts list  
                    pricing_list.append(price)  
                    xx += 1

                features = np.around(np.diff(pricing_list) / pricing_list[:-1] * 100.0, 1) #1=limits to 1 dec  
                    #gets the percent change of stocks

                #print(features)

                if end_price > begin_price:   #with this set of features and % chagnes the ending price from the point of investment was higher  
                    label = 1  
                else:  
                    label = -1  
                bar += 1  
                X.append(features)  
                y.append(label)

            #feature creation  
            except Exception as e:  
                bar += 1                #prevent infinite while loop  
                print(('feature creation',str(e)))



        clf1 = RandomForestClassifier()      #10 = how many classifiers to use  
        clf2 = LinearSVC()  
        clf3 = NuSVC()  
        clf4 = LogisticRegression()

        last_prices = price_list[-context.feature_window:]  
        current_features = np.around(np.diff(last_prices) / last_prices[:-1] * 100.0, 1)

        X.append(current_features)  
        X = preprocessing.scale(X)        #sets all features between 1 and -1


        current_features = X[-1]  
        X = X[:-1]                    #up to -1st but not -1st


        clf1.fit(X,y)                #here are the features and labels that apply.  
        clf2.fit(X,y)  
        clf3.fit(X,y)  
        clf4.fit(X,y)  


        p1 = clf1.predict(current_features) [0]  
        p2 = clf2.predict(current_features) [0]  
        p3 = clf3.predict(current_features) [0]  
        p4 = clf4.predict(current_features) [0]  

        if Counter([p1,p2,p3,p4]).most_common(1)[0][1] >= 4:       #votes says clasifiers must agree  
            p = Counter([p1,p2,p3,p4]).most_common(1)[0][0]        #prediction = like tuple, (number)[occurances][prediction]  
        else:  
            p = 0            #nothing will hapen if if isnt satisfied  

        print(('prediciton',p))

        if p == 1 and ma1 > ma2:  
            order_target_percent(stock,0.11)  
        elif p == -1 and ma1 < ma2:  
            order_target_percent(stock,-0.11)  
    except Exception as e:  
        print(str(e))  


record('Leverage',context.account.leverage)  

machine learning reference page scikit-learn.org/