Selecting Liquid/Illiquid Stocks based on Trading Volume

liquid_stocks.py

# Load packages 
import cvxpy as cvx
import numpy as np
import pandas as pd
import time
import project_tests
import project_helper

import matplotlib.pyplot as plt
%matplotlib inline
plt.style.use('ggplot')
plt.rcParams['figure.figsize'] = (14, 8)

import os
import project_helper
from zipline.data import bundles

from zipline.pipeline import Pipeline
from zipline.pipeline.factors import AverageDollarVolume
from zipline.utils.calendars import get_calendar


# Data Bundle 
# Using Zipline to handle the data 
os.environ['ZIPLINE_ROOT'] = os.path.join(os.getcwd(), '..', '..', 'data', 'US_eod_data')

ingest_func = bundles.csvdir.csvdir_equities(['daily'], project_helper.EOD_BUNDLE_NAME)
bundles.register(project_helper.EOD_BUNDLE_NAME, ingest_func)

print(os.getcwd())
print('Data Registered')

# Build the pipeline engine 
universe = AverageDollarVolume(window_length=120).top(500) 
trading_calendar = get_calendar('NYSE') 
bundle_data = bundles.load(project_helper.EOD_BUNDLE_NAME)
engine = project_helper.build_pipeline_engine(bundle_data, trading_calendar)

# Extract the most liquid 500 stocks in the last 120 days 
universe_end_date = pd.Timestamp('2016-01-05', tz='UTC')

universe_tickers = engine\
    .run_pipeline(
        Pipeline(screen=universe),
        universe_end_date,
        universe_end_date)\
    .index.get_level_values(1)\
    .values.tolist()

print('List of the 500 most liquid stocks in the last 120 days: ')
print(universe_tickers)

You need to have a csv file called, 'US_eod_data.csv', kept inside a 'data' folder for this snippet to work.
US_eod_data should have dates as its index, with stock symbols as its columns. It is supposed to have 'End of Day' or closing prices for each stock on each date.