sentiment_time.py

def time_groups_to_plot_elements(slices, nbins=9):
    """Take the grouped time-sentiment relationships, and break it down into a single point/line for the plot"""
    plot_data = {}
    bins = np.linspace(-1.0, 1.0, nbins)
    print bins
    for k, v in slices.items():
        binned_data = np.digitize(v["sentiment"], bins=bins) - 1
        segments = np.zeros(nbins)
        for bin_id in set(binned_data):
            segments[bin_id] = v["sentiment"][binned_data==bin_id].count()
        segments *= np.sign(bins)
        plot_data[k] = segments
    return plot_data
    
# example processed data:
{'MEGANEGATIVE': post_timestamp
 2016-01-25 07:45:49.341873   -1
 2016-01-26 07:45:49.341873   -0
 2016-01-27 07:45:49.341873   -1
 Name: MEGANEGATIVE, dtype: float64, 'Peachy': post_timestamp
 2016-01-25 07:45:49.341873    0
 2016-01-26 07:45:49.341873    0
 2016-01-27 07:45:49.341873    2
 Name: Peachy, dtype: float64, 'SHINYMETALAPPS': post_timestamp
 2016-01-25 07:45:49.341873    0
 2016-01-26 07:45:49.341873    2
 2016-01-27 07:45:49.341873    1
 Name: SHINYMETALAPPS, dtype: float64, 'cold': post_timestamp
 2016-01-25 07:45:49.341873    -0
 2016-01-26 07:45:49.341873    -2
 2016-01-27 07:45:49.341873   -44
 Name: cold, dtype: float64, 'gud': post_timestamp
 2016-01-25 07:45:49.341873     1
 2016-01-26 07:45:49.341873     2
 2016-01-27 07:45:49.341873    22
 Name: gud, dtype: float64, 'meh': post_timestamp
 2016-01-25 07:45:49.341873    0
 2016-01-26 07:45:49.341873    0
 2016-01-27 07:45:49.341873    0
 Name: meh, dtype: float64, 'nauseating': post_timestamp
 2016-01-25 07:45:49.341873   -1
 2016-01-26 07:45:49.341873   -1
 2016-01-27 07:45:49.341873   -1
 Name: nauseating, dtype: float64, 'warm': post_timestamp
 2016-01-25 07:45:49.341873     2
 2016-01-26 07:45:49.341873    11
 2016-01-27 07:45:49.341873    33
 Name: warm, dtype: float64, 'yuck': post_timestamp
 2016-01-25 07:45:49.341873   -1
 2016-01-26 07:45:49.341873   -1
 2016-01-27 07:45:49.341873   -7
 Name: yuck, dtype: float64}