tutorial/detailed_ workflow. Ipynb quantitative finance qlib Library

Although users can be based on Qlib Configuration of Automatically run the entire Quant Research workflow .

Some advanced users usually want Carefully customize each component In the Quant Explore more in .

If you only want a simple Qlib Example . Quick start and workflow_by_code It may be your better choice .

If you want to know about Quant More details of the study , This notebook may be your better starting point .

We hope this script can be right Quant Tutorials for users interested in details .

This notebook attempts to demonstrate how we use Qlib Build... Step by step Components .

from pprint import pprint
from pathlib import Path
import pandas as pd

MARKET = "csi300"
BENCHMARK = "SH000300"
EXP_NAME = "tutorial_exp"

Users can follow the following steps to use CLI Download data .

In this case , We use the bottom layer API Automatically download data

from qlib.tests.data import GetData
GetData().qlib_data(exists_skip=True)

import qlib
qlib.init()

Check the raw data

at present ,Qlib Support multiple data sources .

from qlib.data import D
D.calendar(start_time='2010-01-01', end_time='2017-12-31', freq='day')[:2]  # calendar data

The basic data  

df = D.features(['SH601216'], ['$open', '$high', '$low', '$close', '$factor'], start_time='2020-05-01', end_time='2020-05-31')   

import plotly.graph_objects as go
fig = go.Figure(data=[go.Candlestick(x=df.index.get_level_values("datetime"),
                open=df['$open'],
                high=df['$high'],
                low=df['$low'],
                close=df['$close'])])
fig.show()