How to convert quantopian ML tutorials to zipline?

Hey,
I want to backtest some ML strategies and came across quantopian/zipline. I saw Simple Machine Learning Example post in quantopian which I want to port in zipline. I have used sentdex tutorials as a guiding tool for writing this. But its giving this error.

ValueError: Expected 2D array, got 1D array instead:  
array=[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.].  
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

The other question is how can I add my externally trained model to this code?

This is my whole code

import pandas as pd  
from collections import OrderedDict  
import pytz  
from zipline.api import order, record, symbol, set_benchmark, order_target_percent, get_open_orders  
import zipline  
import matplotlib.pyplot as plt  
from datetime import datetime  
from sklearn.ensemble import RandomForestClassifier  
from collections import deque  
import numpy as np

full_file_path = "AAPL.csv"  
data = OrderedDict()  
data['AAPL'] = pd.read_csv(full_file_path, index_col=0, parse_dates=['date'])  
data['AAPL'] = data['AAPL'][["open","high","low","close","volume"]]  
print(data['AAPL'].head())


panel=pd.Panel(data)

panel.minor_axis =["open","high","low","close","volume"]  
panel.major_axis = panel.major_axis.tz_localize(pytz.utc)

def initialize(context):  
    context.window_length=10  
    context.classifier=RandomForestClassifier()  
    context.recent_prices=deque(maxlen=context.window_length+2)  
    context.X=deque(maxlen=500)  
    context.Y=deque(maxlen=500)  
    context.predi=0  
    set_benchmark(symbol("AAPL"))


def handle_data(context, data):  
    context.recent_prices.append(data['AAPL'].price)  
    if len(context.recent_prices)==context.window_length+2:  
        changes=np.diff(context.recent_prices)>0  
        context.X.append(changes[:-1])  
        context.Y.append(changes[-1])  
    if len(context.Y)>=100:  
        context.classifier.fit(context.X,context.Y)  
        context.predi=context.classifier.predict(changes[1:])  
        order_target_percent('AAPL',context.predi)  
        record(prediction=int(context.predi))


perf = zipline.run_algorithm(start=datetime(2011, 1, 5, 0, 0, 0, 0, pytz.utc),  
                      end=datetime(2012, 3, 1, 0, 0, 0, 0, pytz.utc),  
                      initialize=initialize,  
                      capital_base=100000,  
                      handle_data=handle_data,  
                      data=panel)

import matplotlib.pyplot as plt  
from matplotlib import style


style.use("ggplot")

perf.portfolio_value.pct_change().fillna(0).add(1).cumprod().sub(1).plot(label='portfolio')  
perf.AAPL.pct_change().fillna(0).add(1).cumprod().sub(1).plot(label='benchmark')  
plt.legend(loc=2)

plt.show()