python数据分析学习笔记七

第七章 信号处理与时间序列

（需要统计学知识）

1 statsmodels 子库

示例代码如下

import pkgutil as pu
import pydoc
import statsmodels as sm

# statmodels版本号
print("statmodels version", sm.__version__)


def clean(astr):
    s = astr
    # remove multiple spaces
    s = ' '.join(s.split())
    s = s.replace('=', '')

    return s


def print_desc(prefix, pkg_path):
    print("pkg_path", pkg_path)
    '''
    :param prefix: 模块名称
    :param pkg_path:模块包路径
    :return:
    '''
    for pkg in pu.iter_modules(path=pkg_path):
        '''Yields (module_loader,模块
         name,子库名
         ispkg)是否'''
        print("pkg", pkg)
        name = prefix + "." + pkg[1]

        # 输出子库名,帮助文档信息
        if pkg[2] == True:
            try:
                docstr = pydoc.plain(pydoc.render_doc(name))
                docstr = clean(docstr)
                start = docstr.find("DESCRIPTION")
                docstr = docstr[start: start + 140]
                print(name, docstr)
            except:
                continue


print_desc("statsmodels", sm.__path__)

运行结果如下:

statmodels version 0.8.0rc1

statsmodels.base

statsmodels.compat

statsmodels.datasets

statsmodels.discrete

statsmodels.distributions

statsmodels.duration

statsmodels.emplike

statsmodels.formula

statsmodels.genmod

statsmodels.graphics

statsmodels.imputation

statsmodels.interface

statsmodels.iolib

statsmodels.miscmodels

statsmodels.multivariate

statsmodels.nonparametric DESCRIPTION Foran overview of this module, see docs/source/nonparametric.rst PACKAGE CONTENTS_kernel_base _smoothers_lowess api bandwidths

statsmodels.regression

statsmodels.resampling

statsmodels.robust

statsmodels.sandbox

statsmodels.src

statsmodels.stats

statsmodels.tools

statsmodels.tsa

 

2 移动平均值

示例代码如下:

import matplotlib.pyplot as plt
import statsmodels.api as sm
from pandas.stats.moments import rolling_mean

data_loader = sm.datasets.sunspots.load_pandas()
df = data_loader.data

year_range = df['YEAR'].values
plt.plot(year_range, df["SUNACTIVITY"].values, label="Original")
plt.plot(year_range, rolling_mean(df, 11)["SUNACTIVITY"].values, label="SMA 11")
plt.plot(year_range, rolling_mean(df, 22)["SUNACTIVITY"].values, label="SMA 22")
plt.legend()
plt.show()

 

 

 

 

方法二:

import matplotlib.pyplot as plt
import statsmodels.api as sm
from pandas.stats.moments import rolling_mean
import pandas.core.generic

data_loader = sm.datasets.sunspots.load_pandas()
df = data_loader.data
df11 = data_loader.data.rolling(window=11, center=False).mean()
df22 = data_loader.data.rolling(window=22, center=False).mean()
year_range = df['YEAR'].values
plt.plot(year_range, df["SUNACTIVITY"].values, label="Original")
# plt.plot(year_range, rolling_mean(df, window=11, center=False)["SUNACTIVITY"].values, label="SMA 11")
# plt.plot(year_range, rolling_mean(df, window=22, center=False)["SUNACTIVITY"].values, label="SMA 22")
plt.plot(year_range, df11["SUNACTIVITY"].values, label="SMA 11")
plt.plot(year_range, df22["SUNACTIVITY"].values, label="SMA 22")
plt.legend()
plt.show()

 

运行结果如下:

 

3 窗口函数

 是定义在一个区间(窗口)上的函数,超出定义,函数值取零,可以用来分析频谱,设计滤波器

import matplotlib.pyplot as plt
import statsmodels.api as sm
from pandas.stats.moments import rolling_window
<