Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- def draw_log_hist(x):
- plt.figure(figsize=(15,15))
- # Feature_array[i] количетсво пользователей, у которых встречалось слово i
- feature_counts = np.asarray(x.astype(bool).sum(axis=0))
- feature_array = feature_counts[0]
- # Количесво слов, которые встречаются у i-пользователей (ОСЬ Y)
- feature_user_counts = np.bincount(feature_array)[1:]
- # 1...len(feature_user_counts)
- user_counts = np.arange(1, len(feature_user_counts) + 1)
- plt.plot(user_counts, feature_user_counts, 'bo')
- plt.gca().set_xscale("log")
- plt.gca().set_yscale("log")
- plt.xlabel("Number of users for whom some feature occured x times")
- return feature_array
- features_counts = draw_log_hist(X)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement