applied K Means for the verbs dataset (not working yet)

estnltk_preprocessing.py

 from estnltk import Text
 from estnltk import Text
 from util import save_dict, load_dict, save_csv, read_csv
 from util import save_dict, load_dict, save_csv, read_csv
+from k_means import plot_k_means
 import pandas as pd
 import pandas as pd
 import matplotlib.pyplot as plt
 import matplotlib.pyplot as plt
 import numpy as np
 import numpy as np
@@ -71,9 +72,26 @@ def construct_df_of_verbs(initial_df):
 		i += 1
 		i += 1
 	verbs_df = pd.DataFrame.from_dict(rows)
 	verbs_df = pd.DataFrame.from_dict(rows)
 	verbs_df = verbs_df[verbs_df['number_of_samples'] != 0]
 	verbs_df = verbs_df[verbs_df['number_of_samples'] != 0]
+	verbs_df = verbs_df.fillna(0)
+	print(verbs_df)
 	save_csv(verbs_df, 'verbs.csv', sep='~', header=True)
 	save_csv(verbs_df, 'verbs.csv', sep='~', header=True)
 	print(verbs_df)
 	print(verbs_df)
 
 
+def transform_df_to_preprocessed_array(df): # divide by the number of samples
+	X = df.drop(['verb', 'number_of_samples'], axis=1)
+	columns = X.columns
+	X = X.values
+	number_of_samples = df['number_of_samples'].values
+	number_of_samples = np.array([number_of_samples]*X.shape[1])
+	number_of_samples = np.swapaxes(number_of_samples, 0, 1)
+	X = X / number_of_samples
+	return X, columns
+
 
 
 df = read_csv('verbs.csv', sep='~', header=0)
 df = read_csv('verbs.csv', sep='~', header=0)
-print(df)
+X, columns = transform_df_to_preprocessed_array(df)
\ No newline at end of file
+K = 5
+plot_k_means(X, K, columns)
+# df = read_csv('cleaned_dataframe.csv', sep='~')
+# df.columns = ['distance', 'noun_like', 'noun_like_form', 'noun_like_pos', 'sentence', 'verb', 'verbs_form']
+# construct_df_of_verbs(df)
\ No newline at end of file

k_means.py

+import numpy as np
+import matplotlib.pyplot as plt
+np.set_printoptions(threshold=np.nan)
+
+def d(u, v): # squared difference
+    diff = u - v
+    return diff.dot(diff)
+
+def cost(X, R, M):
+	cost = 0
+	for k in range(len(M)):
+		diff = X - M[k]
+		sq_distances = (diff * diff).sum(axis=1)
+		cost += (R[:,k] * sq_distances).sum()
+	return cost
+
+
+def plot_k_means(X, K, columns, max_iter=20, beta=1.0, show_plots=True):
+	N, D = X.shape
+	M = np.zeros((K, D)) # means
+	exponents = np.empty((N, K))
+
+	for k in range(K):
+		M[k] = X[np.random.choice(N)]
+
+	costs = np.zeros(max_iter)
+	for i in range(max_iter):
+		for k in range(K):
+			for n in range(N):
+				exponents[n,k] = np.exp(-beta*d(M[k], X[n]))
+
+		R = exponents / exponents.sum(axis=1, keepdims=True)
+		for k in range(K):
+			M[k] = R[:,k].dot(X) / R[:,k].sum()
+
+		costs[i] = cost(X, R, M)
+		# if i > 0:
+		# 	if np.abs(costs[i] - costs[i-1]) < 1e-5:
+		# 		break
+
+	if show_plots:
+		plt.plot(costs)
+		plt.title("Costs")
+		plt.show()
+
+		random_colors = np.random.random((K, 3))
+		colors = R.dot(random_colors)
+		for i in range(X.shape[0]-1):
+			for j in range(i + 1, X.shape[0]-1):
+				plt.scatter(X[:,i], X[:,j], c=colors)
+				plt.xlabel(columns[i])
+				plt.ylabel(columns[j])
+				plt.show()
+
+	return M, R
\ No newline at end of file