add a datsets option to specify the datset you want, add a plot script

analyze.py

@@ -0,0 +1,48 @@
+import csv
+import matplotlib.pyplot as plt
+from scipy import stats
+import pandas as pd
+
+def plot(l):
+    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]
+    plt.bar(labels, l)
+    plt.savefig('plot.png')
+
+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]
+        
+        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
+            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)
+    return stats.spearmanr(results.swap_score, results.valid_acc)[0]
+
+if __name__ == '__main__':
+    print(analyse('output/swap_results.csv'))
+
+
+
+
+
+