zipline quandl bundle not collecting data in run_algorithm() function

Question

I am following a book Trading evolved: Anyone can build a killer trading strategy in Pythom - (section 7: Backtesting trading strategies, page 68) - and I have the following code.

Code & data:

# This ensures that our graphs will be shown properly in the notebook.
%matplotlib inline

#Import pandas as pd

import pandas as pd

# Import Zipline functions that we need
from zipline import run_algorithm
from zipline.api import order_target_percent, symbol

# Import date and time zone libraries
from datetime import datetime
import pytz

# Import visualization
import matplotlib.pyplot as plt


def initialize(context):
    # Which stock to trade
    context.stock = symbol('AAPL')

    # Moving average window
    context.index_average_window = 100

def handle_data(context, data):
    # Request history for the stock
    equities_hist = data.history(context.stock, "close", 
                                 context.index_average_window, "1d")

    # Check if price is above moving average
    if equities_hist[-1] > equities_hist.mean():
        stock_weight = 1.0
    else:
        stock_weight = 0.0

    # Place order
    order_target_percent(context.stock, stock_weight)

def analyze(context, perf):
    fig = plt.figure(figsize=(12, 8))

    # First chart
    ax = fig.add_subplot(311)
    ax.set_title('Strategy Results')
    ax.semilogy(perf['portfolio_value'], linestyle='-', 
                label='Equity Curve', linewidth=3.0)
    ax.legend()
    ax.grid(False)

    # Second chart
    ax = fig.add_subplot(312)
    ax.plot(perf['gross_leverage'], 
            label='Exposure', linestyle='-', linewidth=1.0)
    ax.legend()
    ax.grid(True)

    # Third chart
    ax = fig.add_subplot(313)
    ax.plot(perf['returns'], label='Returns', linestyle='-.', linewidth=1.0)
    ax.legend()
    ax.grid(True)

# Set start and end date
start_date = pd.Timestamp('1996-1-1', tz='utc')
end_date = pd.Timestamp('2018-12-31', tz='utc')

# Fire off the backtest
results = run_algorithm(
    start=start_date, 
    end=end_date, 
    initialize=initialize, 
    analyze=analyze, 
    handle_data=handle_data, 
    capital_base=10000, 
    data_frequency = 'daily', bundle='quandl' 
)

However I get the following error:

FileNotFoundError                         Traceback (most recent call last)
~/anaconda3/envs/zipline_env/lib/python3.6/site-packages/zipline/data/bundles/core.py in most_recent_data(bundle_name, timestamp, environ)
    471             candidates = os.listdir(
--> 472                 pth.data_path([bundle_name], environ=environ),
    473             )

FileNotFoundError: [Errno 2] No such file or directory: '/home/bscuser/.zipline/data/quandl'

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
<ipython-input-4-c4c8f7e5b9b0> in <module>
     75     handle_data=handle_data,
     76     capital_base=10000,
---> 77     data_frequency = 'daily', bundle='quandl'
     78 )

~/anaconda3/envs/zipline_env/lib/python3.6/site-packages/zipline/utils/run_algo.py in run_algorithm(start, end, initialize, capital_base, handle_data, before_trading_start, analyze, data_frequency, bundle, bundle_timestamp, trading_calendar, metrics_set, benchmark_returns, default_extension, extensions, strict_extensions, environ, blotter)
    407         environ=environ,
    408         blotter=blotter,
--> 409         benchmark_spec=benchmark_spec,
    410     )
    411 

~/anaconda3/envs/zipline_env/lib/python3.6/site-packages/zipline/utils/run_algo.py in _run(handle_data, initialize, before_trading_start, analyze, algofile, algotext, defines, data_frequency, capital_base, bundle, bundle_timestamp, start, end, output, trading_calendar, print_algo, metrics_set, local_namespace, environ, blotter, benchmark_spec)
     89         bundle,
     90         environ,
---> 91         bundle_timestamp,
     92     )
     93 

~/anaconda3/envs/zipline_env/lib/python3.6/site-packages/zipline/data/bundles/core.py in load(name, environ, timestamp)
    511         if timestamp is None:
    512             timestamp = pd.Timestamp.utcnow()
--> 513         timestr = most_recent_data(name, timestamp, environ=environ)
    514         return BundleData(
    515             asset_finder=AssetFinder(

~/anaconda3/envs/zipline_env/lib/python3.6/site-packages/zipline/data/bundles/core.py in most_recent_data(bundle_name, timestamp, environ)
    487                 'maybe you need to run: $ zipline ingest -b {bundle}'.format(
    488                     bundle=bundle_name,
--> 489                     timestamp=timestamp,
    490                 ),
    491             )

ValueError: no data for bundle 'quandl' on or before 2022-03-02 19:41:10.170941+00:00
maybe you need to run: $ zipline ingest -b quandl

On the very last line I believe that the problem is to do with the Quandl bundle - data_frequency = 'daily', bundle='quandl'. So my question is how can I get the zipline library to work with the quandl data? or yahoo finance data?

Answer 1

Assuming you properly ingested the quandl bundle (instructions in the book). I believe the free quandl data only runs through 12-31-17, so try these dates (working for me):

start = pd.Timestamp('2003-01-01', tz='UTC') 
end = pd.Timestamp('2017-12-31', tz='UTC')