python机器学习预测_使用Python和机器学习预测未来的股市趋势

python机器学习预测

Note from Towards Data Science’s editors: While we allow independent authors to publish articles in accordance with our rules and guidelines, we do not endorse each author’s contribution. You should not rely on an author’s works without seeking professional advice. See our Reader Terms for details.

Towards Data Science编辑的注意事项： 尽管我们允许独立作者按照我们的 规则和指南 发表文章 ，但我们不认可每位作者的贡献。 您不应在未征求专业意见的情况下依赖作者的作品。 有关 详细信息， 请参见我们的 阅读器条款 。

With the recent volatility of the stock market due to the COVID-19 pandemic, I thought it was a good idea to try and utilize machine learning to predict the near-future trends of the stock market. I’m fairly new to machine learning, and this is my first Medium article so I thought this would be a good project to start off with and showcase.

鉴于最近由于COVID-19大流行而导致的股市波动，我认为尝试利用机器学习来预测股市的近期趋势是一个好主意。 我是机器学习的新手，这是我的第一篇中型文章，所以我认为这是一个很好的项目，首先要进行展示。

This article tackles different topics concerning data science, namely; data collection and cleaning, feature engineering, as well as the creation of machine learning models to make predictions.

本文讨论了与数据科学有关的不同主题，即： 数据收集和清理，功能工程以及创建机器学习模型以进行预测。

Author’s disclaimer: This project is not financial or investment advice. It is not a guarantee that it will provide the correct results most of the time. Therefore you should be very careful and not use this as a primary source of trading insight.

作者免责声明：该项目不是财务或投资建议。 不能保证大部分时间都会提供正确的结果。 因此，您应该非常小心，不要将其用作交易洞察力的主要来源。

You can find all the code on a jupyter notebook on my github:

您可以在我的github上的jupyter笔记本上找到所有代码：

1.进口和数据收集 (1. Imports and Data Collection)

To begin, we include all of the libraries used for this project. I used the yfinance API to gather all of the historical stock market data. It’s taken directly from the yahoo finance website, so it’s very reliable data.

首先，我们包括用于该项目的所有库。 我使用yfinance API收集了所有历史股票市场数据。 它直接来自雅虎财经网站，因此它是非常可靠的数据。

import yfinance as yf
import datetime
import pandas as pd
import numpy as np
from finta import TA
import matplotlib.pyplot as plt


from sklearn import svm
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import VotingClassifier
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import confusion_matrix, classification_report
from sklearn import metrics

We then define some constants that used in data retrieval and data processing. The list with the indicator symbols is useful to help use produce more features for our model.

然后，我们定义一些用于数据检索和数据处理的常量。 带有指示器符号的列表对于帮助使用为我们的模型产生更多功能很有用。

"""
Defining some constants for data mining
"""


NUM_DAYS = 10000     # The number of days of historical data to retrieve
INTERVAL = '1d'     # Sample rate of historical data
symbol = 'SPY'      # Symbol of the desired stock


# List of symbols for technical indicators
INDICATORS = ['RSI', 'MACD', 'STOCH','ADL', 'ATR', 'MOM', 'MFI', 'ROC', 'OBV', 'CCI', 'EMV', 'VORTEX']

Here’s a link where you can find the actual names of some of these features.

在此链接中，您可以找到其中某些功能的实际名称。

Now we pull our historical data from yfinance. We don’t have many features to work with — not particularly useful unless we find a way to normalize them at least or derive more features from them.

现在，我们从yfinance中提取历史数据。 我们没有很多功能可以使用-除非我们找到一种方法至少可以将它们标准化或从中获得更多功能，否则它就没有什么用处。

"""
Next we pull the historical data using yfinance
Rename the column names because finta uses the lowercase names
"""


start = (datetime.date.today() - datetime.timedelta( NUM_DAYS ) )
end = datetime.datetime.today()


data = yf.download(symbol, start=start, end=end, interval=INTERVAL)
data.rename(columns={"Close": 'close',