AI量化与机器学习流程：从数据到模型

这几天的文章讲了数据（hdf5：兼容pandas的dataframe合适量化的存储格式）、特征工程（因子特征工程：基于pandas和talib（代码））、单因子评估（【每周研报复现】AI量化特征工程之alphalens：一套用于分析 alpha 因子的通用工具），今天要说说模型。

先要把金融建模与机器学习流程结合起来：

01 数据准备、特征工程及标注

def feature_engineer(df):
    features = []
    for p in [1, 5, 20, 60]:
        features.append('mom_{}'.format(p))
        df['mom_{}'.format(p)] = df['close'].pct_change(p)

    df['f_return_1'] = np.sign(df['close'].shift(-1) / df['close'] - 1)
    features.append('code')
    features.append('f_return_1')
    print(features)
    df = df[features]
    return df

import pandas as pd

symbols = ['SPX', '000300.SH']
dfs = []
with pd.HDFStore('data/index.h5') as store:
    for symbol in symbols:        df = store[symbol]        df['close'] = df['close'] / df['close'].iloc[0]        df = feature_engineer(df)        dfs.append(df)all = pd.concat(dfs)# all.set_index([all.index,'code'],inplace=True)all.sort_index(ascending=True, level=0, inplace=True)all.dropna(inplace=True)all

这里得到特征工程及标注后的数据集，

这个过程是通用的：

02 划分数据集

import numpy as np
import datetime

def get_date_by_percent(start_date,end_date,percent):
    days = (end_date - start_date).days
    target_days = np.trunc(days * percent)
    target_date = start_date + datetime.timedelta(days=target_days)
    #print days, target_days,target_date
    return target_date

def split_dataset(df,input_column_array,label,split_ratio):
    split_date = get_date_by_percent(df.index[0],df.index[df.shape[0]-1],split_ratio)

    input_data = df[input_column_array]
    output_data = df[label]

    # Create training and test sets
    X_train = input_data[input_data.index < split_date]
    X_test = input_data[input_data.index >= split_date]
    Y_train = output_data[output_data.index < split_date]
    Y_test = output_data[output_data.index >= split_date]

    return X_train,X_test,Y_train,Y_test

03 基准模型

实现三个基准模型，分别为logistic回归、随机森森和SVM。

from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import LinearSVC, SVC

def do_logistic_regression(x_train,y_train):
    classifier = LogisticRegression()
    classifier.fit(x_train, y_train)
    return classifier


def do_random_forest(x_train,y_train):
    classifier = RandomForestClassifier()
    classifier.fit(x_train, y_train)
    return classifier


def do_svm(x_train,y_train):
    classifier = SVC()
    classifier.fit(x_train, y_train)

return classifier

04 测试

def test_predictor(classifier, x_test, y_test):
    pred = classifier.predict(x_test)

    hit_count = 0
    total_count = len(y_test)
    for index in range(total_count):
        if (pred[index]) == (y_test[index]):
            hit_count = hit_count + 1

    hit_ratio = hit_count / total_count
    score = classifier.score(x_test, y_test)
    print("hit_count=%s, total=%s, hit_ratio = %s" % (hit_count, total_count, hit_ratio))

    return hit_ratio, score