Is it over?

.gitignore

@@ -127,12 +127,16 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
 # vscode settings conflic shuns
 .vscode/
-jupyter-notes/merged_games.csv
-datasets/videogames/games_merged.csv
-output.csv
-.gitignore
-output.xlsx
-.gitignore
 datasets/videogames/merged_games.xlsx
+datasets/videogames/games_merged.csv
+datasets/videogames/games_cleanish.csv
+
+jupyter-notes/merged_games.csv
+
+output.csv
+output.xlsx
+
+.gitignore

py_scripts/mining_hq.py

@@ -108,7 +108,7 @@ gammas['Critic_Score_Norm'] = scout.scaling_zscore(gammas, 'Critic_Score')
 print(gammas['Critic_Score_Norm'].head(10))
 
 # Saving all into a file
-gammas.to_csv("output.csv", index=False)
+gammas.to_csv("datasets/videogames/games_cleanish.csv", index=False)
 
 # Need similarity and dissimialrity, scipy time
 # Selecting 5 random rows
@@ -116,4 +116,4 @@ chosen_idx = np.random.choice(len(gammas), replace = False, size = 5)
 sample_rows = gammas.iloc[chosen_idx]
 print(sample_rows.head())
 
-# scout.dissimilarity(sample_rows.select_dtypes(include = np.number))
+scout.dissimilarity(sample_rows)

py_scripts/scout.py

@@ -49,11 +49,15 @@ def scaling_zscore(dataframe, col):
     return stats.zscore(dataframe[col],axis = 0,  nan_policy= "omit")
 
 def dissimilarity(row_arr):
-    for i in len(row_arr):
-        print("| ")
-        for j in len(row_arr):
+    row_arr = row_arr.select_dtypes(include = np.number)
+    row_arr = row_arr.drop('Rank', axis = 1)
+    
+    print("          |  Entry 1 | Entry 2 | Entry 3 | Entry 4 | Entry 5 |")
+    for i in range(len(row_arr)):
+        print("Entry " , i + 1, " | ", end = "")
+        for j in range(len(row_arr)):
             eucDist = distance.euclidean(row_arr.iloc[i], row_arr.iloc[j])
-            print(f"Dissim {i}{j}: {eucDist} |")
+            print(" {:#.6g} |".format(eucDist), end = "")
         print("\n")
 
 def scaling_range(datashitter, col):