如何利用Jupyter Notekook做初步分析

这篇文章主要介绍如何利用Jupyter Notekook做初步分析，文中介绍的非常详细，具有一定的参考价值，感兴趣的小伙伴们一定要看完！

最近一段时间都是Jupyter Notebook做策略的最初版本设计，就是行情导入画图一类。

之前做个dataframe做分析容易，这个算是简化版本。

1. 新建一个DataAnalyzer 类，这个简单很多，支持从csv和mongodb导入行情数据，和从1分钟k线整合不同分钟k线

   下面是导入1分钟螺纹钢数据，整合为5分钟K线

from pymongo import MongoClient, ASCENDINGimport pandas as pdimport numpy as npfrom datetime import datetimeimport talibimport matplotlib.pyplot as pltimport scipy.stats as st%matplotlib inline%config InlineBackend.figure_format = 'retina'class DataAnalyzer(object):    """    """    def __init__(self, exportpath="C:\Project\\", datformat=['datetime', 'high', 'low', 'open', 'close','volume']):        self.mongohost = None        self.mongoport = None        self.db = None        self.collection = None        self.df = pd.DataFrame()        self.exportpath = exportpath        self.datformat = datformat        self.startBar = 2        self.endBar = 12        self.step = 2        self.pValue = 0.015    def db2df(self, db, collection, start, end, mongohost="localhost", mongoport=27017, export2csv=False):        """读取MongoDB数据库行情记录，输出到Dataframe中"""        self.mongohost = mongohost        self.mongoport = mongoport        self.db = db        self.collection = collection        dbClient = MongoClient(self.mongohost, self.mongoport, connectTimeoutMS=500)        db = dbClient[self.db]        cursor = db[self.collection].find({'datetime':{'$gte':start, '$lt':end}}).sort("datetime",ASCENDING)        self.df = pd.DataFrame(list(cursor))        self.df = self.df[self.datformat]        self.df = self.df.reset_index(drop=True)        path = self.exportpath + self.collection + ".csv"        if export2csv == True:            self.df.to_csv(path, index=True, header=True)        return self.df    def csv2df(self, csvpath, dataname="csv_data", export2csv=False):        """读取csv行情数据，输入到Dataframe中"""        csv_df = pd.read_csv(csvpath)        self.df = csv_df[self.datformat]        self.df["datetime"] = pd.to_datetime(self.df['datetime'])        # self.df["high"] = self.df['high'].astype(float)        # self.df["low"] = self.df['low'].astype(float)        # self.df["open"] = self.df['open'].astype(float)        # self.df["close"] = self.df['close'].astype(float)        # self.df["volume"] = self.df['volume'].astype(int)        self.df = self.df.reset_index(drop=True)        path = self.exportpath + dataname + ".csv"        if export2csv == True:            self.df.to_csv(path, index=True, header=True)        return self.df    def df2Barmin(self, inputdf, barmins, crossmin=1, export2csv=False):        """输入分钟k线dataframe数据，合并多多种数据，例如三分钟/5分钟等，如果开始时间是9点1分，crossmin = 0；如果是9点0分，crossmin为1"""        dfbarmin = pd.DataFrame()        highBarMin = 0        lowBarMin = 0        openBarMin = 0        volumeBarmin = 0        datetime = 0        for i in range(0, len(inputdf) - 1):            bar = inputdf.iloc[i, :].to_dict()            if openBarMin == 0:                openBarmin = bar["open"]            if highBarMin == 0:                highBarMin = bar["high"]            else:                highBarMin = max(bar["high"], highBarMin)            if lowBarMin == 0:                lowBarMin = bar["low"]            else:                lowBarMin = min(bar["low"], lowBarMin)            closeBarMin = bar["close"]            datetime = bar["datetime"]            volumeBarmin += int(bar["volume"])            # X分钟已经走完            if not (bar["datetime"].minute + crossmin) % barmins:  # 可以用X整除                # 生成上一X分钟K线的时间戳                barMin = {'datetime': datetime, 'high': highBarMin, 'low': lowBarMin, 'open': openBarmin,                          'close': closeBarMin, 'volume' : volumeBarmin}                dfbarmin = dfbarmin.append(barMin, ignore_index=True)                highBarMin = 0                lowBarMin = 0                openBarMin = 0                volumeBarmin = 0        if export2csv == True:            dfbarmin.to_csv(self.exportpath + "bar" + str(barmins)+ str(self.collection) + ".csv", index=True, header=True)        return dfbarminexportpath = "C:\\Project\\"DA = DataAnalyzer(exportpath)#数据库导入start = datetime.strptime("20190920", '%Y%m%d')end = datetime.now()dfrb8888 = DA.db2df(db="VnTrader_1Min_Db", collection="rb8888", start = start, end = end,export2csv=True)dfrb5min = DA.df2Barmin(dfrb8888,5,crossmin=1, export2csv=True)dfrb5min.tail()

2. 计算5分钟K线的参照，包括标准差，rsi，5分钟均线，和40分钟均线

logdata = pd.DataFrame()logdata['close'] =(dfrb5min['close'])# logdata['tr'] = talib.ATR(np.array(dfrb8888['high']), np.array(dfrb8888['low']), np.array(dfrb8888['close']) ,1)# logdata['atr'] = talib.ATR(np.array(dfrb8888['high']), np.array(dfrb8888['low']), np.array(dfrb8888['close']) ,20)logdata['std20'] = talib.STDDEV( np.array(dfrb5min['close']) ,20)logdata['rsi30'] = talib.RSI(np.array(dfrb5min['close']) ,30)logdata['sma5'] = talib.SMA(np.array(dfrb5min['close']) ,5)logdata['sma40'] = talib.SMA(np.array(dfrb5min['close']) ,40)logdata.plot(subplots=True,figsize=(18,16))

3. 使用快慢均线策略，显示买入卖出点

closeArray = np.array(logdata['close'])listup,listdown = [],[]for i in range(1,len(logdata['close'])):    if logdata.loc[i,'sma5'] > logdata.loc[i,'sma40'] and logdata.loc[i-1,'sma5'] < logdata.loc[i-1,'sma40']:        listup.append(i)    elif logdata.loc[i,'sma5'] < logdata.loc[i,'sma40'] and logdata.loc[i-1,'sma5'] > logdata.loc[i-1,'sma40']:        listdown.append(i)fig=plt.figure(figsize=(18,6))plt.plot(closeArray, color='y', lw=2.)plt.plot(closeArray, '^', markersize=5, color='r', label='UP signal', markevery=listup)plt.plot(closeArray, 'v', markersize=5, color='g', label='DOWN signal', markevery=listdown)plt.legend()plt.show()

以上是"如何利用Jupyter Notekook做初步分析"这篇文章的所有内容，感谢各位的阅读！希望分享的内容对大家有帮助，更多相关知识，欢迎关注行业资讯频道！