76 lines
2.3 KiB
Python
76 lines
2.3 KiB
Python
import csv
|
|
import matplotlib.pyplot as plt
|
|
from scipy import stats
|
|
import pandas as pd
|
|
import argparse
|
|
|
|
def plot(l, thousands, filename):
|
|
lenth = len(l)
|
|
threshold = [0, 10000, 20000, 30000, 40000, 50000, 60000, 70000]
|
|
labels = ['0-10k', '10k-20k,', '20k-30k', '30k-40k', '40k-50k', '50k-60k', '60k-70k']
|
|
l = [i/lenth for i in l]
|
|
l = l[:7]
|
|
thousands = thousands[60:]
|
|
thousands_labels = [str(i) + 'k' for i in range(60, 70)]
|
|
plt.figure(figsize=(8, 6))
|
|
plt.subplots_adjust(top=0.85)
|
|
plt.title('Distribution of Swap Scores over 60k')
|
|
plt.bar(thousands_labels, thousands)
|
|
for i, v in enumerate(thousands):
|
|
plt.text(i, v + 0.01, str(v), ha='center', va='bottom')
|
|
plt.savefig(filename + '_60k.png')
|
|
|
|
datasets = filename.split('_')[-1].split('.')[0]
|
|
plt.figure(figsize=(8, 6))
|
|
plt.subplots_adjust(top=0.85)
|
|
# plt.ylim(0,0.3)
|
|
plt.title('Distribution of Swap Scores in ' + datasets)
|
|
plt.bar(labels, l)
|
|
for i, v in enumerate(l):
|
|
plt.text(i, v + 0.01, str(round(v, 2)), ha='center', va='bottom')
|
|
plt.savefig(filename)
|
|
|
|
def analyse(filename):
|
|
l = [0 for i in range(10)]
|
|
scores = []
|
|
count = 0
|
|
best_value = -1
|
|
with open(filename) as file:
|
|
reader = csv.reader(file)
|
|
header = next(reader)
|
|
data = [row for row in reader]
|
|
thousands = [0 for i in range(70)]
|
|
|
|
for row in data:
|
|
score = row[0]
|
|
best_value = max(best_value, float(score))
|
|
# print(score)
|
|
ind = float(score) // 10000
|
|
ind = int(ind)
|
|
l[ind] += 1
|
|
thousands[int(float(score) // 1000)] += 1
|
|
acc = row[1]
|
|
index = row[2]
|
|
datas = list(zip(score, acc, index))
|
|
scores.append(score)
|
|
print(max(scores))
|
|
results = pd.DataFrame(datas, columns=['swap_score', 'valid_acc', 'index'])
|
|
print(results['swap_score'].max())
|
|
print(best_value)
|
|
plot(l, thousands, filename + '.png')
|
|
return stats.spearmanr(results.swap_score, results.valid_acc)[0]
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--filename', type=str, help='Filename to analyze', default='swap_results.csv')
|
|
|
|
args = parser.parse_args()
|
|
|
|
print(analyse('output' + '/' + args.filename))
|
|
|
|
|
|
|
|
|
|
|
|
|