Can Pandas plot a histogram of dates?

Question

I\'ve taken my Series and coerced it to a datetime column of dtype=datetime64[ns] (though only need day resolution...not sure how to change).

i         


        

Answer 1

Rendered example

Example Code

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""Create random datetime object."""

# core modules
from datetime import datetime
import random

# 3rd party modules
import pandas as pd
import matplotlib.pyplot as plt


def visualize(df, column_name='start_date', color='#494949', title=''):
    """
    Visualize a dataframe with a date column.

    Parameters
    ----------
    df : Pandas dataframe
    column_name : str
        Column to visualize
    color : str
    title : str
    """
    plt.figure(figsize=(20, 10))
    ax = (df[column_name].groupby(df[column_name].dt.hour)
                         .count()).plot(kind="bar", color=color)
    ax.set_facecolor('#eeeeee')
    ax.set_xlabel("hour of the day")
    ax.set_ylabel("count")
    ax.set_title(title)
    plt.show()


def create_random_datetime(from_date, to_date, rand_type='uniform'):
    """
    Create random date within timeframe.

    Parameters
    ----------
    from_date : datetime object
    to_date : datetime object
    rand_type : {'uniform'}

    Examples
    --------
    >>> random.seed(28041990)
    >>> create_random_datetime(datetime(1990, 4, 28), datetime(2000, 12, 31))
    datetime.datetime(1998, 12, 13, 23, 38, 0, 121628)
    >>> create_random_datetime(datetime(1990, 4, 28), datetime(2000, 12, 31))
    datetime.datetime(2000, 3, 19, 19, 24, 31, 193940)
    """
    delta = to_date - from_date
    if rand_type == 'uniform':
        rand = random.random()
    else:
        raise NotImplementedError('Unknown random mode \'{}\''
                                  .format(rand_type))
    return from_date + rand * delta


def create_df(n=1000):
    """Create a Pandas dataframe with datetime objects."""
    from_date = datetime(1990, 4, 28)
    to_date = datetime(2000, 12, 31)
    sales = [create_random_datetime(from_date, to_date) for _ in range(n)]
    df = pd.DataFrame({'start_date': sales})
    return df


if __name__ == '__main__':
    import doctest
    doctest.testmod()
    df = create_df()
    visualize(df)