代码之家 › 专栏 › 技术社区 › polonius11

用熊猫数据阅读器进行python回归建模

matplotlib numpy pandas python

polonius11 · 技术社区 · 6 年前

我正在尝试构建一个函数,它将为任何库存提取数据,然后绘制回归图。但是,我遇到了与源数据有关的问题。我的问题是-如何在熊猫数据框架中绘制时间序列,并绘制随时间变化的线性趋势?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()

这是我通过数据帧传递数据的尝试

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()

3 回复 | 直到 6 年前

user115215 6 年前

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()

SamrajM 6 年前

plt.scatter(data_SP.index,data_SP['close'])

import matplotlib.pyplot as plt
import numpy as np
from datetime import datetime
pd.core.common.is_list_like = pd.api.types.is_list_like
from pandas_datareader import data, wb

start = datetime(2017, 8, 1)
end = datetime(2018, 7, 30)
data_SP = data.DataReader('JPM', 'iex', start, end)

plt.scatter(data_SP.index,data_SP['close'])

dates changes link

import datetime as dt
data_df['Date'] = pd.to_datetime(data_df['Date'])
data_df['Date']=data_df['Date'].map(dt.datetime.toordinal)

polonius11 6 年前

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)