Bin plotting

scratch_16.py

import matplotlib
matplotlib.use("TkAgg")
import matplotlib.pyplot as plt
import scipy.stats as stats
import  numpy as np



def plot_results_for_bin_size(size, pd_result, centre_on_mean = False):
    bins = get_bins_for_size(size, pd_result, centre_on_mean = centre_on_mean)
    results = calculate_results_for_bins(bins, pd_result)
    avg_results = [x.mean() for x in results]
    centre_bins = [np.mean([bins[idx], bins[idx - 1]]) for idx in range(len(bins))[1:]]

    plt.plot(centre_bins, avg_results)

    ans = print_t_stats(results)

    return ans


def print_t_stats(results):
    t_results = []
    print("For each bin:")
    for idx in range(len(results))[1:]:
        t_stat = stats.ttest_ind(results[idx], results[idx-1], axis=0, equal_var=True)
        t_results.append(t_stat)
        print(t_stat)
    print("Comparing final and first bins:")
    t_stat = stats.ttest_ind(results[-1], results[0], axis=0, equal_var=True)
    t_results.append(t_stat)
    print(t_stat)

    return t_results

def get_bins_for_size(size, pd_result, centre_on_mean = False):
    if centre_on_mean:
        centre = pd_result.x.mean()
    else:
        centre = 0

    lower_quantiles = quantile_in_range(size, pd_result, min=centre-0.001)
    upper_quantiles = quantile_in_range(size, pd_result, max=centre+0.001)
    return lower_quantiles[:-1]+[centre]+upper_quantiles[1:]

def quantile_in_range(size, pd_result, min=-9999., max=9999.):
    xvar = pd_result.x
    signed_distribution = xvar[(xvar>min) & (xvar<max)]
    quantile_ranges = get_quantile_ranges(size)
    quantile_points = [signed_distribution.quantile(q) for q in quantile_ranges]

    return quantile_points

def get_quantile_ranges(size):
    quantile_ranges = np.arange(0,1.0000001,1.0/size)
    return quantile_ranges

def calculate_results_for_bins(bins, pd_result):
    results = []
    for idx in range(len(bins))[1:]:
        selected_results = pd_result[(pd_result.x>bins[idx-1]) &  (pd_result.x < bins[idx])]
        results.append(selected_results.y)
    return results