add format plot codes

analyze.py

@@ -2,13 +2,23 @@ import csv
 import matplotlib.pyplot as plt
 from scipy import stats
 import pandas as pd
+import argparse
 
-def plot(l):
+def plot(l,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/15625 for i in l]
     l = l[:7]
+    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)
-    plt.savefig('plot.png')
+    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)]
@@ -35,11 +45,16 @@ def analyse(filename):
     results = pd.DataFrame(datas, columns=['swap_score', 'valid_acc', 'index'])
     print(results['swap_score'].max())
     print(best_value)
-    plot(l)
+    plot(l, filename + '.png')
     return stats.spearmanr(results.swap_score, results.valid_acc)[0]
 
 if __name__ == '__main__':
-    print(analyse('output/swap_results.csv'))
+    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))