Blame view
volia/stats.py
7.85 KB
9a2c6b4d0 New file that hel... |
1 2 3 4 5 6 7 8 9 10 11 |
import argparse import os import core.data import math import numpy as np import scipy.stats import pickle import matplotlib.pyplot as plt import matplotlib.colors as mcolors |
d27fe6fcc add utt2dur stati... |
12 |
from utils import SubCommandRunner |
9a2c6b4d0 New file that hel... |
13 |
from cycler import cycler |
9bb5ff657 Adding n argument... |
14 |
|
d27fe6fcc add utt2dur stati... |
15 |
def pred_distribution(predictions: str, labels: str, labelencoder: str, outdir: str): |
9bb5ff657 Adding n argument... |
16 17 |
''' Distribution of the prediction. |
9a2c6b4d0 New file that hel... |
18 |
|
9bb5ff657 Adding n argument... |
19 20 21 22 23 |
For each label, we plot the distribution of the class predicted. For example, for each character, we plot the distribution of the characters predicted. Another example, for each speaker, we plot the distribution of the characters predicted. ''' |
9a2c6b4d0 New file that hel... |
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
predictions = core.data.read_id_values(args.predictions, float) labels = core.data.read_labels(args.labels) le = None with open(args.labelencoder, "rb") as f: le = pickle.load(f) stats = {} print("PREDICTIONS ---------------------------") for id_, predictions_ in predictions.items(): label = labels[id_][0] if label not in stats: stats[label] = { "nb_utt": 1, "predictions": np.expand_dims(predictions_, axis=0) } else: stats[label]["nb_utt"] = stats[label]["nb_utt"] + 1 stats[label]["predictions"] = np.append(stats[label]["predictions"], np.expand_dims(predictions_, axis=0), axis=0) |
9a2c6b4d0 New file that hel... |
43 44 45 46 47 48 49 50 |
colors = [ "darkorange", "red", "blue" ] custom_cycler = (cycler(color=list(mcolors.TABLEAU_COLORS)) * cycler(linestyle=['-', '--', '-.'])) |
9bb5ff657 Adding n argument... |
51 |
print("CALCULATING ---------------------------") |
9a2c6b4d0 New file that hel... |
52 53 54 55 56 57 |
for label, stats_ in stats.items(): plt.gca().set_prop_cycle(custom_cycler) stats_mean = np.mean(stats_["predictions"], axis=0) stats_std = np.std(stats_["predictions"], axis=0) |
9bb5ff657 Adding n argument... |
58 |
|
9a2c6b4d0 New file that hel... |
59 60 61 62 63 64 65 66 67 68 69 |
#print(label) #print(stats_mean) #print(stats_std) kwargs = dict(alpha=0.5) for i in range(stats_["predictions"].shape[1]): label_str = le.inverse_transform([i])[0] #plt.hist(stats_["predictions"][:, i], bins=10, label=label_str, **kwargs) mu = stats_mean[i] variance = stats_std[i] * stats_std[i] sigma = stats_std[i] |
9a2c6b4d0 New file that hel... |
70 71 72 73 74 75 76 77 |
print(f"{i}: mu {mu}, var {variance}, sigma {sigma}") #x_values = np.arange(-1, 5, 0.1) #y_values = scipy.stats.norm(mu, variance) #y = scipy.stats.norm.pdf(x,mean,std) #plt.plot(x_values, y_values.pdf(x_values,)) |
9bb5ff657 Adding n argument... |
78 |
|
9a2c6b4d0 New file that hel... |
79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
#x, step = np.linspace(mu - 3*sigma, mu + 3*sigma, 1000, retstep=True) x = np.linspace(0, 1, 1000) #x = np.linspace(mu - 3*sigma, mu + 3*sigma, 1000) #x, step = np.linspace(0, 1, 1000, retstep=True) P = scipy.stats.norm.cdf(x, mu, sigma) #print(step) plt.plot(x, P, label=label_str, **kwargs) #plt.savefig("simple_gaussian.pdf") plt.legend() plt.savefig(os.path.join(args.outdir, f"{label}_prediction_cdf.pdf")) plt.clf() |
d27fe6fcc add utt2dur stati... |
93 |
print("Decisions") |
9bb5ff657 Adding n argument... |
94 95 96 97 98 99 100 101 102 103 104 105 106 |
def pred_distribution_wt_sel(predictions: str, n: int, labels: str, labelencoder: str, outdir: str): ''' Distribution of the predictions with selection process. 1) For each dimension, select the n individus with the maximum values for the focused dimension. We name S_i the set of n selected individus for the dimension i. 2) For each subset S_i, we plot the distribution of each dimension. ''' le = None with open(args.labelencoder, "rb") as f: le = pickle.load(f) |
765b51bc7 Little modificati... |
107 108 |
keys_preds, matrix_preds = core.data.read_features_with_matrix(predictions) |
9bb5ff657 Adding n argument... |
109 110 111 112 113 114 115 116 117 118 119 120 |
colors = [ "darkorange", "red", "blue" ] custom_cycler = (cycler(color=list(mcolors.TABLEAU_COLORS)) * cycler(linestyle=['-', '--', '-.'])) kwargs = dict(alpha=0.5) stats_of = open(os.path.join(args.outdir, f"stats.txt"), "w") |
765b51bc7 Little modificati... |
121 |
for j in range(matrix_preds.shape[1]): |
9bb5ff657 Adding n argument... |
122 123 |
label_focused = le.inverse_transform([j])[0] |
765b51bc7 Little modificati... |
124 |
indices = (-matrix_preds[:, j]).argsort()[:n] |
9bb5ff657 Adding n argument... |
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 |
print(f"LABEL: {label_focused}", file=stats_of) print(f"INDICE: {j}", file=stats_of) print("indices", file=stats_of) print(indices, file=stats_of) print("Best values", file=stats_of) print(matrix_preds[indices, j], file=stats_of) print("All dimensions of best values", file=stats_of) print(matrix_preds[indices], file=stats_of) # Use it to build a plot. pred_ = matrix_preds[indices] stats_mean = np.mean(pred_, axis=0) stats_std = np.std(pred_, axis=0) for i in range(matrix_preds.shape[1]): label_str = le.inverse_transform([i])[0] mu = stats_mean[i] variance = stats_std[i] * stats_std[i] sigma = stats_std[i] print(f"{i}: mu {mu}, var {variance}, sigma {sigma}") x = np.linspace(0, 1, 1000) P = scipy.stats.norm.cdf(x, mu, sigma) plt.plot(x, P, label=label_str, **kwargs) plt.legend() plt.savefig(os.path.join(args.outdir, f"{label_focused}_prediction_cdf.pdf")) plt.clf() stats_of.close() |
765b51bc7 Little modificati... |
156 |
pass |
d27fe6fcc add utt2dur stati... |
157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
def utt2dur(utt2dur: str, labels: str): if labels == None: pass else: pass durations = [] with open(utt2dur, "r") as f: for line in f: splited = line.replace(" ", "").split(" ") durations.append(float(splited[1])) durations = np.asarray(durations, dtype=float) print(durations.shape) mean = np.mean(durations) std = np.std(durations) |
9a2c6b4d0 New file that hel... |
174 |
|
d27fe6fcc add utt2dur stati... |
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 |
print(f"mean: {mean}") print(f"std: {std}") if __name__ == "__main__": # Parser parser = argparse.ArgumentParser(description="Statistics") subparsers = parser.add_subparsers(title="actions") # pred-distribution parser_pred_dist = subparsers.add_parser("pred-distribution", help="plot distributions of prediction through labels") parser_pred_dist.add_argument("--predictions", type=str, help="prediction file", required=True) parser_pred_dist.add_argument("--labels", type=str, help="label file", required=True) parser_pred_dist.add_argument("--labelencoder", type=str, help="label encode pickle file", required=True) parser_pred_dist.add_argument("--outdir", type=str, help="output file", required=True) parser_pred_dist.set_defaults(which="pred_distribution") |
765b51bc7 Little modificati... |
192 193 194 |
# pred-distribution-with-selection parser_pred_dist_wt_sel = subparsers.add_parser("pred-distribution-with-selection", help="plot distributions of prediction through labels with a selection of the n best records by column/class prediction.") parser_pred_dist_wt_sel.add_argument("--predictions", type=str, help="prediction file", required=True) |
417942fcd Specifying that "... |
195 |
parser_pred_dist_wt_sel.add_argument("-n", type=int, help="Number of maximum selected for each prediction y_i.", required=True) |
765b51bc7 Little modificati... |
196 197 198 199 |
parser_pred_dist_wt_sel.add_argument("--labels", type=str, help="label file", required=True) parser_pred_dist_wt_sel.add_argument("--labelencoder", type=str, help="label encode pickle file", required=True) parser_pred_dist_wt_sel.add_argument("--outdir", type=str, help="output file", required=True) parser_pred_dist_wt_sel.set_defaults(which="pred_distribution_with_selection") |
9bb5ff657 Adding n argument... |
200 |
|
d27fe6fcc add utt2dur stati... |
201 202 203 204 205 206 207 208 209 210 211 |
# duration-stats parser_utt2dur = subparsers.add_parser("utt2dur", help="distribution of utt2dur") parser_utt2dur.add_argument("--utt2dur", type=str, help="utt2dur file", required=True) parser_utt2dur.add_argument("--labels", type=str, default=None, help="labels file") parser_utt2dur.set_defaults(which="utt2dur") # Parse args = parser.parse_args() # Run commands runner = SubCommandRunner({ |
765b51bc7 Little modificati... |
212 213 |
"pred_distribution": pred_distribution, "pred_distribution_with_selection": pred_distribution_wt_sel, |
d27fe6fcc add utt2dur stati... |
214 215 216 217 |
"utt2dur": utt2dur }) runner.run(args.which, args.__dict__, remove="which") |