cmantas · March 22, 2019 15:16 · Mar 22, 2019
diff --git a/cdf.py b/cdf.py
@@ -0,0 +1,21 @@
+def cdf(data, label, show = True):
+    data_size=len(data)
+
+    # Set bins edges
+    data_set=sorted(set(data))
+    bins=np.append(data_set, data_set[-1]+1)
+
+    # Use the histogram function to bin the data
+    counts, bin_edges = np.histogram(data, bins=bins, density=False)
+
+    counts=counts.astype(float)/data_size
+
+    # Find the cdf
+    cdf = np.cumsum(counts)
+
+    # Plot the cdf
+    plt.plot(bin_edges[0:-1], cdf,linestyle='--', label=label)
+
+    plt.ylabel('cdf')
+    plt.legend()
+    plt.show()