python - 属性错误 : 'numpy.int64' object has no attribute 'to_timestamp'

Question

我正在尝试从 python 数据框中绘制时间序列。代码如下。

import requests
from bs4 import BeautifulSoup
import pandas as pd
import datetime
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.dates import DateFormatter, YearLocator, MonthLocator
plt.style.use('ggplot')


def plot(df, filename, heading=None):

    fig, ax = plt.subplots(figsize=(8, 4))

    min_date = None
    max_date = None
    for col_name in df.columns.values:

        # plot the column
        col = df[col_name]
        col = col[col.notnull()] # drop NAs
        dates = [zzz.to_timestamp().date() for zzz in col.index]
        ax.plot_date(x=dates, y=col, fmt='-', label=col_name,
            tz=None, xdate=True, ydate=False, linewidth=1.5)

        # establish the date range for the data
        if min_date:
            min_date = min(min_date, min(dates))
        else:
            min_date = min(dates)
        if max_date:
            max_date = max(max_date, max(dates))
        else:
            max_date = max(dates)

    # give a bit of space at each end of the plot - aesthetics
    span = max_date - min_date
    extra = int(span.days * 0.03) * datetime.timedelta(days=1)
    ax.set_xlim([min_date - extra, max_date + extra])

    # format the x tick marks
    ax.xaxis.set_major_formatter(DateFormatter('%Y'))
    ax.xaxis.set_minor_formatter(DateFormatter('\n%b'))
    ax.xaxis.set_major_locator(YearLocator())
    ax.xaxis.set_minor_locator(MonthLocator(bymonthday=1, interval=2))

    # grid, legend and yLabel
    ax.grid(True)
    ax.legend(loc='best', prop={'size':'x-small'})
    ax.set_ylabel('Percent')

    # heading
    if heading:
        fig.suptitle(heading, fontsize=12)
    fig.tight_layout(pad=1.5)

    # footnote
    fig.text(0.99, 0.01, 'nse-timeseries-plot', ha='right',
        va='bottom', fontsize=8, color='#999999')

    # save to file
    fig.savefig(filename, dpi=125)


    url = "https://www.google.com/finance/historical?cid=207437&startdate=Jan%201%2C%201971&enddate=Jul%201%2C%202017&start={0}&num=30"
    how_many_pages=138
    start=0

    for i in range(how_many_pages):
        new_url = url.format(start)
        page = requests.get(new_url)
        soup = BeautifulSoup(page.content, "lxml")
        table = soup.find_all('table', class_='gf-table historical_price')[0]

        columns_header = [th.getText() for th in table.findAll('tr')[0].findAll('th')]
        data_rows=table.findAll('tr')[1:]
        data=[[td.getText() for td in data_rows[i].findAll(['td'])] for i in range(len(data_rows))]

        if start == 0:
            final_df = pd.DataFrame(data, columns=columns_header)
        else:
            df = pd.DataFrame(data, columns=columns_header)
            final_df = pd.concat([final_df, df],axis=0)
        start += 30
        final_df.to_csv('nse_data.csv', sep='\t', encoding='utf-8')


    plot(final_df,'nsetsplot')

当我运行代码时出现错误AttributeError: 'numpy.int64' 对象没有属性 'to_timestamp'

当我这样做的时候

dates = [zzz.to_timestamp().date() for zzz in col.index]

我在 Windows 7 (x86_64) 上使用 Anaconda 64 位

Answer 1

显然，您的 DataFrame 的索引不是 pandas.PeriodIndex。相反，索引似乎包含整数。您发布的代码要求数据框的索引为 PeriodIndex。例如

In [36]: df
Out[36]: 
                a         b
2012-01  1.457900  7.084201
2012-02  1.775861  6.448277
2012-03  1.069051  7.861898

In [37]: df.index
Out[37]: PeriodIndex(['2012-01', '2012-02', '2012-03'], dtype='period[M]', freq='M')

当索引类型正确时，以下代码(类似于您发布的代码中的行)起作用:

In [39]: dates = [zzz.to_timestamp().date() for zzz in df.index]

In [40]: dates
Out[40]: 
[datetime.date(2012, 1, 1),
 datetime.date(2012, 2, 1),
 datetime.date(2012, 3, 1)]