使用Pandas Data Reader进行Python回归建模
使用Pandas Data Reader进行Python回归建模
提问于 2018-07-29 07:07:44
我正在尝试构建一个函数，该函数将拉取任何股票的数据，然后绘制回归图。然而，我遇到了源数据的问题。我的问题是-如何获取熊猫数据帧中的时间序列，并绘制随时间的线性趋势？我的代码如下：
此代码将生成回归：
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import numpy as np
rng = np.random.RandomState(1)
x = 10 * rng.rand(50)
y = 2 * x - 5 + rng.randn(50)
plt.scatter(x, y);
plt.show()
from sklearn.linear_model import LinearRegression
model = LinearRegression(fit_intercept=True)
model.fit(x[:, np.newaxis], y)
xfit = np.linspace(0, 10, 1000)
yfit = model.predict(xfit[:, np.newaxis])
plt.scatter(x, y)
plt.plot(xfit, yfit);
plt.show()这是我尝试通过dataframe传递数据
from datetime import datetime
import pandas_datareader.data as web
start = datetime(2017, 8, 1)
end = datetime(2018, 7, 30)
data_SP = web.DataReader('JPM', 'iex', start, end)
y = dates # not sure how to get here?
plt.scatter(data['close'], y);
plt.show()
from sklearn.linear_model import LinearRegression
model = LinearRegression(fit_intercept=True)
model.fit(data['close'][:, np.newaxis], y)
xfit = np.linspace(0, 10, 1000)
yfit = model.predict(xfit[:, np.newaxis])
plt.scatter(data['close'], y)
plt.plot(xfit, yfit);
plt.show()回答 2
Stack Overflow用户
回答已采纳
发布于 2018-07-29 07:47:23
回归不能接受datetime对象，必须转换为number类型：
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import numpy as np
from datetime import datetime
import pandas as pd
pd.core.common.is_list_like = pd.api.types.is_list_like
from sklearn.linear_model import LinearRegression
import pandas_datareader.data as web
start = datetime(2017, 8, 1)
end = datetime(2018, 7, 30)
data_SP = web.DataReader('JPM', 'iex', start, end)
dates = list(map(lambda x: datetime.strptime(x,"%Y-%m-%d"),list(data_SP.index)))
days_since = list(map(lambda x: (x-start).days,dates))
model = LinearRegression(fit_intercept=True)
model.fit(np.array(days_since)[:, np.newaxis],data_SP['close'])
yfit = model.predict(np.array(days_since)[:, np.newaxis])
plt.figure()
plt.scatter(dates, yfit)
plt.scatter(dates, data_SP['close'])
plt.xlabel('date')
plt.ylabel('close')
plt.show()如果使用百分比更改，则需要考虑NaN。
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import numpy as np
from datetime import datetime
import pandas as pd
pd.core.common.is_list_like = pd.api.types.is_list_like
from sklearn.linear_model import LinearRegression
import pandas_datareader.data as web
start = datetime(2017, 8, 1)
end = datetime(2018, 7, 30)
data_SP = web.DataReader('JPM', 'iex', start, end)
dates = list(map(lambda x: datetime.strptime(x,"%Y-%m-%d"),list(data_SP.index)))
days_since = list(map(lambda x: (x-start).days,dates))
model = LinearRegression(fit_intercept=True)
model.fit(np.array(days_since)[1:][:, np.newaxis],data_SP['close'].pct_change(1)[1:]) # <------------
yfit = model.predict(np.array(days_since)[:, np.newaxis])
plt.figure()
plt.scatter(dates, yfit)
plt.scatter(dates, data_SP['close'].pct_change(1))
plt.xlabel('date')
plt.ylabel('close')
plt.show()
Stack Overflow用户
发布于 2018-07-29 22:10:12
我已经将代码调整为以下内容。它将产生显示超过基准的回报的视觉效果。代码有很多方向可供选择。例如，我们可以让它对标普500指数中的所有500只股票进行循环，找出相对于指数回报最好的股票，或者我们可以让它以1个月的周期循环所有500只股票，并根据历史计算出什么时候持有最好的股票。视觉效果对分析来说是一种很好的触感。
import matplotlib.pyplot as plt
import numpy as np
from datetime import datetime
import pandas
from sklearn.linear_model import LinearRegression
import pandas_datareader.data as pdr
def close_price_trending(analysis):
model = LinearRegression(fit_intercept=True)
model.fit(np.array(days_since)[:, np.newaxis],data_sample_processed[analysis])
yfit = model.predict(np.array(days_since)[:, np.newaxis])
plt.scatter(dates, data_sample_processed[analysis])
plt.scatter(dates, yfit)
plt.xlabel('date')
plt.ylabel('close')
plt.show()
def return_excess_benchmark1(analysis, benchmark):
fig = plt.figure()
ax = fig.add_subplot(111)
fig.subplots_adjust(top=0.85)
ax.set_title(str(analysis) + ' O/U ' + str(benchmark))
plt.scatter(dates, (1 + data_sample_processed[analysis]).cumprod() - (1 + data_sample_processed[benchmark]).cumprod())
model = LinearRegression(fit_intercept=True)
model.fit(np.array(days_since)[:, np.newaxis],(1 + data_sample_processed[analysis]).cumprod() - (1 + data_sample_processed[benchmark]).cumprod())
yfit = model.predict(np.array(days_since)[:, np.newaxis])
plt.scatter(dates, yfit)
plt.xlabel('date')
plt.ylabel('close')
fig.show()
# get and process data
start = datetime(2015, 8, 1)
end = datetime(2018, 7, 30)
Symbol_List = ['GSLC', 'AGG', 'JPM','CAR', 'IVV', 'DSI', 'VTI']
data = pandas.concat([pdr.DataReader(s, 'iex', start, end).rename(columns={'close': s})
for s in Symbol_List], axis=1)
data_sample = data[Symbol_List]
data_sample_processed = data_sample.pct_change()
data_sample_processed = data_sample_processed.fillna(0)
dates = list(map(lambda x: datetime.strptime(x,"%Y-%m-%d"),list(data_sample_processed.index)))
days_since = list(map(lambda x: (x-start).days,dates))
# start analysis
analysis_symbol_1 = 'DSI'
analysis_symbol_2 = 'GSLC'
benchmark_1 = 'VTI'
return_excess_benchmark1(analysis_symbol_1, benchmark_1)
return_excess_benchmark1(analysis_symbol_2, benchmark_1)页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/51575927
复制相关文章
相似问题