del _diamonds in files name

examples/convex_hull_full.py

@@ -59,7 +59,7 @@ for combo in combos:
     df_loss.loc[idx, 'end_eps'] = end_eps
     df_loss.loc[idx, 'end_sample'] = end_sample
     idx += 1
-df_loss.to_csv(f'./end_eps_for_{df_names[0]}_in_pair_w_{df_names[1]}_full_diamonds.csv', index=False)
+df_loss.to_csv(f'./end_eps_for_{df_names[0]}_in_pair_w_{df_names[1]}_full.csv', index=False)
 
 
 # second dataset
@@ -74,7 +74,7 @@ for combo in combos:
     df_loss.loc[idx, 'end_eps'] = end_eps
     df_loss.loc[idx, 'end_sample'] = end_sample
     idx += 1
-df_loss.to_csv(f'./end_eps_for_{df_names[1]}_in_pair_w_{df_names[0]}_full_diamonds.csv', index=False)
+df_loss.to_csv(f'./end_eps_for_{df_names[1]}_in_pair_w_{df_names[0]}_full.csv', index=False)
 
 # computation of intersection values with all points (outliers included) without sampling of instances
 logging.info(f'BEFORE DBSCAN, {df_names[1]} is fixed')

examples/convex_hull_sampled.py

@@ -62,7 +62,7 @@ for combo in combos:
     df_loss.loc[idx, 'end_eps'] = end_eps
     df_loss.loc[idx, 'end_sample'] = end_sample
     idx += 1
-df_loss.to_csv(f'./end_eps_for_{df_names[0]}_in_pair_w_{df_names[1]}_full_diamonds.csv', index=False)
+df_loss.to_csv(f'./end_eps_for_{df_names[0]}_in_pair_w_{df_names[1]}_full.csv', index=False)
 
 
 # second dataset
@@ -77,7 +77,7 @@ for combo in combos:
     df_loss.loc[idx, 'end_eps'] = end_eps
     df_loss.loc[idx, 'end_sample'] = end_sample
     idx += 1
-df_loss.to_csv(f'./end_eps_for_{df_names[1]}_in_pair_w_{df_names[0]}_full_diamonds.csv', index=False)
+df_loss.to_csv(f'./end_eps_for_{df_names[1]}_in_pair_w_{df_names[0]}_full.csv', index=False)
 
 ### the second dataframe is considered at its full size, the size of the first dataset is altered
 # computation of intersection values with all points (outliers included) and sampling of instances
@@ -87,7 +87,7 @@ for combo in combos:
     df_curr = compute_intersections(combo = combo, df_1 = df_1, df_2 = df_2, df_names = df_names,
                                     bools_1 = [], bools_2 = [], first_fixed = False, size = size)
     df_1_in_2 = pd.concat([df_1_in_2, df_curr])
-df_1_in_2.to_csv(f"./sampled_{df_names[0]}_and_full_{df_names[1]}_all_points_diamonds.csv", index=False)
+df_1_in_2.to_csv(f"./sampled_{df_names[0]}_and_full_{df_names[1]}_all_points.csv", index=False)
 
 # computation of intersection values after outlier removal and sampling of instances
 logging.info(f'AFTER DBSCAN, {df_names[1]} is fixed')
@@ -96,7 +96,7 @@ for combo, bool_1, bool_2 in zip(combos, result_bools_1, result_bools_2):
     df_curr = compute_intersections(combo = combo, df_1 = df_1, df_2 = df_2, df_names = df_names,
                                     bools_1 = bool_1, bools_2 = bool_2, first_fixed = False, size = size)
     df_1_in_2 = pd.concat([df_1_in_2, df_curr])
-df_1_in_2.to_csv(f"./full_{df_names[0]}_and_full_{df_names[1]}_wo_outliers_diamonds.csv", index=False)
+df_1_in_2.to_csv(f"./full_{df_names[0]}_and_full_{df_names[1]}_wo_outliers.csv", index=False)
 
 ### symmetric case: the first dataframe is considered at its full size, the size of the second dataset is altered
 # computation of intersection values with all points (outliers included) and sampling of instances
@@ -106,7 +106,7 @@ for combo in combos:
     df_curr = compute_intersections(combo = combo, df_1 = df_1, df_2 = df_2, df_names = df_names,
                                     bools_1 = [], bools_2 = [], first_fixed = True, size = size)
     df_1_in_2 = pd.concat([df_1_in_2, df_curr])
-df_1_in_2.to_csv(f"./sampled_{df_names[1]}_and_full_{df_names[0]}_all_points_diamonds.csv", index=False)
+df_1_in_2.to_csv(f"./sampled_{df_names[1]}_and_full_{df_names[0]}_all_points.csv", index=False)
 
 # computation of intersection values after outlier removal and sampling of instances
 logging.info(f'AFTER DBSCAN, {df_names[0]} is fixed')
@@ -115,4 +115,4 @@ for combo, bool_1, bool_2 in zip(combos, result_bools_1, result_bools_2):
     df_curr = compute_intersections(combo = combo, df_1 = df_1, df_2 = df_2, df_names = df_names,
                                     bools_1 = bool_1, bools_2 = bool_2, first_fixed = True, size = size)
     df_1_in_2 = pd.concat([df_1_in_2, df_curr])
-df_1_in_2.to_csv(f"./sampled_{df_names[1]}_and_full_{df_names[0]}_wo_outliers_diamonds.csv", index=False)
+df_1_in_2.to_csv(f"./sampled_{df_names[1]}_and_full_{df_names[0]}_wo_outliers.csv", index=False)

examples/further_analysis.py

@@ -19,7 +19,7 @@ path_to_ch_outputs = f'{path_to_tables}/full_*' #FIXME: fix to the path where th
 # intersection values the combination of features with the smallest intersection values are found. Condition for the search is
 # the lower fence, values that are smaller are considered as those that may include important features (i.e. those that
 # discriminate between the sets). If the lower fence is negative, no such combinations are found
-df = pd.read_csv(f'{path_to_table}/full_{df_pairs[0]}_and_full_{df_pairs[1]}_wo_outliers_diamonds.csv') #FIXME: fix to the path where the table is stored
+df = pd.read_csv(f'{path_to_table}/full_{df_pairs[0]}_and_full_{df_pairs[1]}_wo_outliers.csv') #FIXME: fix to the path where the table is stored
 df_mean = df.groupby(['Name', 'Parameters']).mean()
 df_mean = df_mean.reset_index()
 
@@ -37,7 +37,7 @@ enrich_df = pd.concat([enrich_1, enrich_2]).reset_index(drop = True)
 if not enrich_df.empty:
     # if the table is not empty it contains the list of important features, their count in 'bad' combinations (those with low
     # intersection values) and 'good' combinations (those that are higher than the lower fence), odds and p-values
-    enrich_df.to_csv(f'./important_parameters_{df_pairs[0]}_and_{df_pairs[1]}_diamonds.csv', index=False)
+    enrich_df.to_csv(f'./important_parameters_{df_pairs[0]}_and_{df_pairs[1]}.csv', index=False)
 else:
     logging.info('Bad parameters not found')
 

examples/machine_learning.py

@@ -25,4 +25,4 @@ df_2['df_name'] = 'second_df'
 # df_name: name of a dataframe (in target variable) to be set at 1 in the classification problem
 # corr_coef: float, coefficient of acceptable correlation between features. If more, then one of the correlated features will be dropped
 result = classify(df_1 = df_1, df_2 = df_2, target = 'df_name', df_name = 'first_df', corr_coef = 0.9)
-result.to_csv('./Classification_diamonds.csv', index=False)
+result.to_csv('./Classification.csv', index=False)