finished cleaning the dataframe

estnltk_preprocessing.py

@@ -46,10 +46,13 @@ def clean_dataframe():
 	df.columns = ['distance', 'noun_like', 'noun_like_form', 'noun_like_pos', 'sentence', 'verb', 'verbs_form']
 	df = df[pd.notnull(df['noun_like_form'])] # remove examples with null forms
 	df = df[~df['noun_like_form'].str.contains('\|')] # remove example with several forms
+	df = df[~df['sentence'].str.contains('A post shared by')]
 	df = df[df['noun_like_form'] != '?'] # remove examples with unknown forms
 	save_csv(df, 'cleaned_dataframe.csv', sep='~')
 	print(df[df['distance'] > 100]['sentence'])
-	plt.scatter(df['distance'], df['noun_like_form'], alpha=0.2, c='k')
+	plt.scatter(df['distance'], df['noun_like_pos'], alpha=0.05, c='green')
 	plt.show()
 
+# df = verbs_dict_to_df()
+# save_csv(df, 'verbs_with_noun_likes.csv', sep='~')
 clean_dataframe()
\ No newline at end of file