您好,登錄后才能下訂單哦!
這篇文章主要介紹如何利用Jupyter Notekook做初步分析,文中介紹的非常詳細,具有一定的參考價值,感興趣的小伙伴們一定要看完!
最近一段時間都是Jupyter Notebook做策略的最初版本設計,就是行情導入畫圖一類。
之前做個dataframe做分析容易,這個算是簡化版本。
新建一個DataAnalyzer 類,這個簡單很多,支持從csv和mongodb導入行情數據,和從1分鐘k線整合不同分鐘k線
下面是導入1分鐘螺紋鋼數據,整合為5分鐘K線
from pymongo import MongoClient, ASCENDING import pandas as pd import numpy as np from datetime import datetime import talib import matplotlib.pyplot as plt import 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): """讀取MongoDB數據庫行情記錄,輸出到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): """讀取csv行情數據,輸入到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): """輸入分鐘k線dataframe數據,合并多多種數據,例如三分鐘/5分鐘等,如果開始時間是9點1分,crossmin = 0;如果是9點0分,crossmin為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分鐘已經走完 if not (bar["datetime"].minute + crossmin) % barmins: # 可以用X整除 # 生成上一X分鐘K線的時間戳 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 dfbarmin exportpath = "C:\\Project\\" DA = DataAnalyzer(exportpath) #數據庫導入 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. 計算5分鐘K線的參照,包括標準差,rsi,5分鐘均線,和40分鐘均線
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. 使用快慢均線策略,顯示買入賣出點
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”這篇文章的所有內容,感謝各位的閱讀!希望分享的內容對大家有幫助,更多相關知識,歡迎關注億速云行業資訊頻道!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。