Update TextAnalisisSpacy.py

TextAnalisisSpacy.py

@@ -79,8 +79,9 @@ class TextAnalisisSpacy():
               dic[cat].append(dic[cat][len(dic[cat])-1])
               dic[cat].append(dic[cat][len(dic[cat])-1])
           df_n = pd.DataFrame(dic)
           df_n = pd.DataFrame(dic)
           splot = sb.heatmap(df_n.transpose()).set_title(columna)
           splot = sb.heatmap(df_n.transpose()).set_title(columna)
-        plt.show()
-        if export:
+        if export == False:
+          plt.show()
+        else:
           splot.get_figure().savefig(columna+"-"+ type_g+".jpg", bbox_inches='tight')
           splot.get_figure().savefig(columna+"-"+ type_g+".jpg", bbox_inches='tight')
           plt.clf()
           plt.clf()
 
 
@@ -276,7 +277,7 @@ class TextAnalisisSpacy():
         display(df_freq_palabras.transpose())
         display(df_freq_palabras.transpose())
         df_freq_palabras_tr = df_freq_palabras.transpose()
         df_freq_palabras_tr = df_freq_palabras.transpose()
         df_freq_palabras_tr.to_csv("POS_"+ str(pos)+"_freq.csv") 
         df_freq_palabras_tr.to_csv("POS_"+ str(pos)+"_freq.csv") 
-        return df_freq_palabras.transpose()
+      return df_freq_palabras.transpose()
 
 
     def lexical_diversity(self):
     def lexical_diversity(self):
       # Lexical diversity for each text
       # Lexical diversity for each text
@@ -392,15 +393,15 @@ class TextAnalisisSpacy():
       # Univariate feature selection
       # Univariate feature selection
       from sklearn.feature_selection import SelectKBest
       from sklearn.feature_selection import SelectKBest
       from sklearn.feature_selection import f_classif, mutual_info_classif
       from sklearn.feature_selection import f_classif, mutual_info_classif
-      print('Highest scoring '+ k +' features with f_classif...')
-      kbest_classif = SelectKBest(f_classif, k) # Elimina todo menos las k características de puntuación más alta
+      print('Highest scoring '+ str(k) +' features with f_classif...')
+      kbest_classif = SelectKBest(f_classif, k=k) # Elimina todo menos las k características de puntuación más alta
       X_classif = kbest_classif.fit_transform(X, y)
       X_classif = kbest_classif.fit_transform(X, y)
       print('Selected columns:',kbest_classif.get_feature_names_out(self.df.columns.values[2:]))
       print('Selected columns:',kbest_classif.get_feature_names_out(self.df.columns.values[2:]))
       display(pd.DataFrame(X_classif))
       display(pd.DataFrame(X_classif))
       pd.DataFrame(X_classif).to_csv("f_classif.csv") 
       pd.DataFrame(X_classif).to_csv("f_classif.csv") 
 
 
       print('Highest scoring '+ str(k) +' features with mutual_info_classif...')
       print('Highest scoring '+ str(k) +' features with mutual_info_classif...')
-      kbest_mut = SelectKBest(mutual_info_classif, k)
+      kbest_mut = SelectKBest(mutual_info_classif, k=k)
       X_mut = kbest_mut.fit_transform(X, y)
       X_mut = kbest_mut.fit_transform(X, y)
       print('Selected columns:', kbest_mut.get_feature_names_out(self.df.columns.values[2:]))
       print('Selected columns:', kbest_mut.get_feature_names_out(self.df.columns.values[2:]))
       display(pd.DataFrame(X_mut))
       display(pd.DataFrame(X_mut))