update over 60k plots

analyze.py

@@ -4,16 +4,26 @@ from scipy import stats
 import pandas as pd
 import argparse
 
-def plot(l,filename):
+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/15625 for i in l]
+    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.ylim(0,0.3)
     plt.title('Distribution of Swap Scores in ' + datasets)
     plt.bar(labels, l)
     for i, v in enumerate(l):
@@ -29,6 +39,7 @@ def analyse(filename):
         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]
@@ -37,6 +48,7 @@ def analyse(filename):
             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))
@@ -45,7 +57,7 @@ def analyse(filename):
     results = pd.DataFrame(datas, columns=['swap_score', 'valid_acc', 'index'])
     print(results['swap_score'].max())
     print(best_value)
-    plot(l, filename + '.png')
+    plot(l, thousands, filename + '.png')
     return stats.spearmanr(results.swap_score, results.valid_acc)[0]
 
 if __name__ == '__main__':