AttributeError: 'numpy.int64' object has no attribute 'to_timestamp'

Question

I am trying to plot a time series from a python data frame. The code is below.

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')

When I run the code I get the error AttributeError: 'numpy.int64' object has no attribute 'to_timestamp'

when I do

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

I am using Anaconda 64-bit on Windows 7 (x86_64)

Solution

Apparently the index of your DataFrame is not a pandas.PeriodIndex. Instead, the index appears hold integers. The code that you posted requires the index of the data frame to be a PeriodIndex. E.g.

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')

When the index is the correct type, the following code (similar to the line in the code you posted) works:

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)]