diff --git a/__pycache__/run.cpython-38.pyc b/__pycache__/run.cpython-38.pyc index 22d455c..2c0d091 100644 Binary files a/__pycache__/run.cpython-38.pyc and b/__pycache__/run.cpython-38.pyc differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/031611c241ba479d18e1372b83d0b576/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/031611c241ba479d18e1372b83d0b576/output.pkl deleted file mode 100644 index 3c95086..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/031611c241ba479d18e1372b83d0b576/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/06dd5713420a922c24ec4885229fa897/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/06dd5713420a922c24ec4885229fa897/metadata.json new file mode 100644 index 0000000..305540e --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/06dd5713420a922c24ec4885229fa897/metadata.json @@ -0,0 +1 @@ +{"duration": 1.665640115737915, "input_args": {"Data": " F1_p2 F2_l1p F1+F2 |F1-F2| F1xF2 F1/F2 F2/F1\n0 6.25 1.458615 7.708615 4.791385 9.116344 4.284887 0.233378\n1 3.61 1.308333 4.918333 2.301667 4.723081 2.759237 0.362419\n2 4.41 1.386294 5.796294 3.023706 6.113558 3.181143 0.314352\n3 3.24 1.360977 4.600977 1.879023 4.409564 2.380644 0.420054\n4 4.84 1.386294 6.226294 3.453706 6.709665 3.491322 0.286424\n.. ... ... ... ... ... ... ...\n145 0.09 1.386294 1.476294 1.296294 0.124766 0.064921 15.403271\n146 0.04 1.568616 1.608616 1.528616 0.062745 0.025500 39.215398\n147 0.04 1.435085 1.475085 1.395085 0.057403 0.027873 35.877113\n148 0.04 1.547563 1.587563 1.507563 0.061903 0.025847 38.689063\n149 0.04 1.458615 1.498615 1.418615 0.058345 0.027423 36.465376\n\n[150 rows x 7 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/078851605dad0fde46d0717720886edd/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/078851605dad0fde46d0717720886edd/output.pkl new file mode 100644 index 0000000..e2fc056 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/078851605dad0fde46d0717720886edd/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/08076429e1f4a912207d8f1318e23956/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/08076429e1f4a912207d8f1318e23956/output.pkl deleted file mode 100644 index 03f86f8..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/08076429e1f4a912207d8f1318e23956/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/0ac4b1e38d060ee7705418ad7d40ac9b/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/0ac4b1e38d060ee7705418ad7d40ac9b/output.pkl deleted file mode 100644 index 7ed6830..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/0ac4b1e38d060ee7705418ad7d40ac9b/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/0b5341d3e1474cd2b4d28e1033a5e75b/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/0b5341d3e1474cd2b4d28e1033a5e75b/metadata.json new file mode 100644 index 0000000..a054dd7 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/0b5341d3e1474cd2b4d28e1033a5e75b/metadata.json @@ -0,0 +1 @@ +{"duration": 15.683412075042725, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13\n0 1 0 145 0 150 63 233 1 2.3 0 3 0 1\n1 0 0 130 0 187 37 250 1 3.5 1 2 0 2\n2 0 2 130 0 172 41 204 0 1.4 0 1 0 2\n3 0 2 120 0 178 56 236 1 0.8 1 1 0 2\n4 0 2 120 1 163 57 354 0 0.6 1 0 0 2\n.. .. .. ... .. ... .. ... .. ... ... ... ... ...\n298 0 1 140 1 123 57 241 0 0.2 1 0 0 3\n299 0 1 110 0 132 45 264 1 1.2 1 3 0 3\n300 1 1 144 0 141 68 193 1 3.4 1 0 2 3\n301 0 1 130 1 115 57 131 1 1.2 1 0 1 3\n302 0 1 130 0 174 57 236 0 0.0 0 1 1 2\n\n[303 rows x 13 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.1436350297118406,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.143635035,\n max_delta_step=0, max_depth=11, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=196, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/1276da95d3d21f94d4712976522769ea/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/1276da95d3d21f94d4712976522769ea/metadata.json new file mode 100644 index 0000000..94f5119 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/1276da95d3d21f94d4712976522769ea/metadata.json @@ -0,0 +1 @@ +{"duration": 2.59732985496521, "input_args": {"Data": " F1_l10 F3 F4\n0 0.397940 6.3 6.0\n1 0.278754 5.8 5.1\n2 0.322219 7.1 5.9\n3 0.255273 6.3 5.6\n4 0.342423 6.5 5.8\n.. ... ... ...\n145 -0.522879 4.8 1.4\n146 -0.698970 5.1 1.6\n147 -0.698970 4.6 1.4\n148 -0.698970 5.3 1.5\n149 -0.698970 5.0 1.4\n\n[150 rows x 3 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/155fb13ac5302f6e83e8dee4e6e50e10/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/155fb13ac5302f6e83e8dee4e6e50e10/metadata.json new file mode 100644 index 0000000..cb7934b --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/155fb13ac5302f6e83e8dee4e6e50e10/metadata.json @@ -0,0 +1 @@ +{"duration": 1.2182409763336182, "input_args": {"Data": " F1 F2 F3 F4_l2\n0 2.5 3.3 6.3 2.584963\n1 1.9 2.7 5.8 2.350497\n2 2.1 3.0 7.1 2.560715\n3 1.8 2.9 6.3 2.485427\n4 2.2 3.0 6.5 2.536053\n.. ... ... ... ...\n145 0.3 3.0 4.8 0.485427\n146 0.2 3.8 5.1 0.678072\n147 0.2 3.2 4.6 0.485427\n148 0.2 3.7 5.3 0.584963\n149 0.2 3.3 5.0 0.485427\n\n[150 rows x 4 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/15b0b603c741872ef31ad44a4ac4bc66/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/15b0b603c741872ef31ad44a4ac4bc66/metadata.json new file mode 100644 index 0000000..9b13272 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/15b0b603c741872ef31ad44a4ac4bc66/metadata.json @@ -0,0 +1 @@ +{"duration": 1.2176530361175537, "input_args": {"Data": " F1_p2 F2_l1p F3_em1 F4_l2\n0 6.25 1.458615 543.571910 2.584963\n1 3.61 1.308333 329.299560 2.350497\n2 4.41 1.386294 1210.967074 2.560715\n3 3.24 1.360977 543.571910 2.485427\n4 4.84 1.386294 664.141633 2.536053\n.. ... ... ... ...\n145 0.09 1.386294 120.510418 0.485427\n146 0.04 1.568616 163.021907 0.678072\n147 0.04 1.435085 98.484316 0.485427\n148 0.04 1.547563 199.336810 0.584963\n149 0.04 1.458615 147.413159 0.485427\n\n[150 rows x 4 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/194682c7ed5242f27ddde485d72aa28c/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/194682c7ed5242f27ddde485d72aa28c/output.pkl new file mode 100644 index 0000000..72f0881 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/194682c7ed5242f27ddde485d72aa28c/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/1d757a543a7ff69019ec13d167f09684/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/1d757a543a7ff69019ec13d167f09684/metadata.json new file mode 100644 index 0000000..ca314e1 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/1d757a543a7ff69019ec13d167f09684/metadata.json @@ -0,0 +1 @@ +{"duration": 7.925899028778076, "input_args": {"Data": " F1_p2 F2_l1p F3_em1 F1+F2 F2+F3 F1+F3 F1+F2+F3 |F1-F2| ... F1/F3 F3/F1 F1/F2/F3 F1/F3/F2 F2/F3/F1 F2/F1/F3 F3/F1/F2 F3/F2/F1\n0 6.25 1.458615 543.571910 7.708615 545.030525 549.821910 551.280525 4.791385 ... 0.011498 86.971506 0.007883 0.007883 0.000429 0.000429 59.626087 59.626087\n1 3.61 1.308333 329.299560 4.918333 330.607893 332.909560 334.217893 2.301667 ... 0.010963 91.218715 0.008379 0.008379 0.001101 0.001101 69.721338 69.721338\n2 4.41 1.386294 1210.967074 5.796294 1212.353369 1215.377074 1216.763369 3.023706 ... 0.003642 274.595709 0.002627 0.002627 0.000260 0.000260 198.078933 198.078933\n3 3.24 1.360977 543.571910 4.600977 544.932887 546.811910 548.172887 1.879023 ... 0.005961 167.769108 0.004380 0.004380 0.000773 0.000773 123.271123 123.271123\n4 4.84 1.386294 664.141633 6.226294 665.527927 668.981633 670.367927 3.453706 ... 0.007288 137.219346 0.005257 0.005257 0.000431 0.000431 98.982835 98.982835\n.. ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...\n145 0.09 1.386294 120.510418 1.476294 121.896712 120.600418 121.986712 1.296294 ... 0.000747 1339.004639 0.000539 0.000539 0.127817 0.127817 965.887676 965.887676\n146 0.04 1.568616 163.021907 1.608616 164.590523 163.061907 164.630523 1.528616 ... 0.000245 4075.547682 0.000156 0.000156 0.240553 0.240553 2598.180750 2598.180750\n147 0.04 1.435085 98.484316 1.475085 99.919400 98.524316 99.959400 1.395085 ... 0.000406 2462.107891 0.000283 0.000283 0.364293 0.364293 1715.653571 1715.653571\n148 0.04 1.547563 199.336810 1.587563 200.884372 199.376810 200.924372 1.507563 ... 0.000201 4983.420249 0.000130 0.000130 0.194089 0.194089 3220.173803 3220.173803\n149 0.04 1.458615 147.413159 1.498615 148.871774 147.453159 148.911774 1.418615 ... 0.000271 3685.328978 0.000186 0.000186 0.247369 0.247369 2526.594694 2526.594694\n\n[150 rows x 27 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/1ed1e3543e5b8c0b8ed8273e2b6d737b/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/1ed1e3543e5b8c0b8ed8273e2b6d737b/metadata.json deleted file mode 100644 index adfb1b2..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/1ed1e3543e5b8c0b8ed8273e2b6d737b/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 7.470085859298706, "input_args": {"Data": " F1 F2 F3 F4\n0 2.5 3.3 6.3 6.0\n1 1.9 2.7 5.8 5.1\n2 2.1 3.0 7.1 5.9\n3 1.8 2.9 6.3 5.6\n4 2.2 3.0 6.5 5.8\n.. ... ... ... ...\n145 0.3 3.0 4.8 1.4\n146 0.2 3.8 5.1 1.6\n147 0.2 3.2 4.6 1.4\n148 0.2 3.7 5.3 1.5\n149 0.2 3.3 5.0 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=9.044474534604408, gamma=0.1, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/25fee0cbdc3277a2ced8f885a76d1e60/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/25fee0cbdc3277a2ced8f885a76d1e60/output.pkl new file mode 100644 index 0000000..9e165a9 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/25fee0cbdc3277a2ced8f885a76d1e60/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/2a6079ddbc93fa25176f9d1f3009a610/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/2a6079ddbc93fa25176f9d1f3009a610/output.pkl new file mode 100644 index 0000000..2c336f6 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/2a6079ddbc93fa25176f9d1f3009a610/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/2bc28dfd99c9f6a65f1d74e67cd622bb/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/2bc28dfd99c9f6a65f1d74e67cd622bb/output.pkl deleted file mode 100644 index 2487c0c..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/2bc28dfd99c9f6a65f1d74e67cd622bb/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/2ea39cd41bf1eea844679842787364a7/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/2ea39cd41bf1eea844679842787364a7/metadata.json deleted file mode 100644 index e2cbdf5..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/2ea39cd41bf1eea844679842787364a7/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 2.0144307613372803, "input_args": {"Data": " F1 F2_mms F3 F4 F1xF3\n0 2.5 0.541667 6.3 6.0 15.75\n1 1.9 0.291667 5.8 5.1 11.02\n2 2.1 0.416667 7.1 5.9 14.91\n3 1.8 0.375000 6.3 5.6 11.34\n4 2.2 0.416667 6.5 5.8 14.30\n.. ... ... ... ... ...\n145 0.3 0.416667 4.8 1.4 1.44\n146 0.2 0.750000 5.1 1.6 1.02\n147 0.2 0.500000 4.6 1.4 0.92\n148 0.2 0.708333 5.3 1.5 1.06\n149 0.2 0.541667 5.0 1.4 1.00\n\n[150 rows x 5 columns]", "clf": "SVC(C=44.03816499590499, gamma=0.01, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/2ea39cd41bf1eea844679842787364a7/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/2ea39cd41bf1eea844679842787364a7/output.pkl deleted file mode 100644 index 30bd2fa..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/2ea39cd41bf1eea844679842787364a7/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/38e2478f77650eab4b3915634ec05396/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/38e2478f77650eab4b3915634ec05396/output.pkl new file mode 100644 index 0000000..6710d21 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/38e2478f77650eab4b3915634ec05396/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/3ce1789aa381a937c9967ca360bdcf7f/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/3ce1789aa381a937c9967ca360bdcf7f/metadata.json new file mode 100644 index 0000000..2fb9f72 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/3ce1789aa381a937c9967ca360bdcf7f/metadata.json @@ -0,0 +1 @@ +{"duration": 5.265573978424072, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8\n0 72 50 33.6 6 35 0.627 0 148\n1 64 32 23.3 8 0 0.672 0 183\n2 40 33 43.1 0 35 2.288 168 137\n3 50 26 31.0 3 32 0.248 88 78\n4 70 53 30.5 2 45 0.158 543 197\n.. .. .. ... .. .. ... ... ...\n763 62 33 22.5 9 0 0.142 0 89\n764 76 63 32.9 10 48 0.171 180 101\n765 70 27 36.8 2 27 0.340 0 122\n766 72 30 26.2 5 23 0.245 112 121\n767 70 23 30.4 1 31 0.315 0 93\n\n[768 rows x 8 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=0.9728230822718118,\n eta=0.15918739742144755, gamma=0, gpu_id=-1,\n importance_type='gain', interaction_constraints='',\n learning_rate=0.11327384412356725, max_delta_step=0, max_depth=6,\n min_child_weight=1, missing=nan, monotone_constraints='()',\n n_estimators=130, n_jobs=12, num_parallel_tree=1,\n probability=True, random_state=42, reg_alpha=0, reg_lambda=1,\n scale_pos_weight=1, silent=True, subsample=0.9666339466107166,\n tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/3cfbe165b148a5cf6d67371edc55c4ad/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/3cfbe165b148a5cf6d67371edc55c4ad/metadata.json new file mode 100644 index 0000000..bf23723 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/3cfbe165b148a5cf6d67371edc55c4ad/metadata.json @@ -0,0 +1 @@ +{"duration": 16.90331506729126, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13\n0 1 0 145 0 150 63 233 1 2.3 0 3 0 1\n1 0 0 130 0 187 37 250 1 3.5 1 2 0 2\n2 0 2 130 0 172 41 204 0 1.4 0 1 0 2\n3 0 2 120 0 178 56 236 1 0.8 1 1 0 2\n4 0 2 120 1 163 57 354 0 0.6 1 0 0 2\n.. .. .. ... .. ... .. ... .. ... ... ... ... ...\n298 0 1 140 1 123 57 241 0 0.2 1 0 0 3\n299 0 1 110 0 132 45 264 1 1.2 1 3 0 3\n300 1 1 144 0 141 68 193 1 3.4 1 0 2 3\n301 0 1 130 1 115 57 131 1 1.2 1 0 1 3\n302 0 1 130 0 174 57 236 0 0.0 0 1 1 2\n\n[303 rows x 13 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.1436350297118406,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.143635035,\n max_delta_step=0, max_depth=11, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=147, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/3e3c713cadf06d7020b3fd615022bba0/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/3e3c713cadf06d7020b3fd615022bba0/output.pkl new file mode 100644 index 0000000..52cdb78 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/3e3c713cadf06d7020b3fd615022bba0/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/3f0623bf82584c5a558248b65b02e98a/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/3f0623bf82584c5a558248b65b02e98a/output.pkl deleted file mode 100644 index 5dc1d53..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/3f0623bf82584c5a558248b65b02e98a/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/48a4d9833395644d39fa812fe54613a6/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/48a4d9833395644d39fa812fe54613a6/output.pkl new file mode 100644 index 0000000..15c8679 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/48a4d9833395644d39fa812fe54613a6/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/4dd4312c4a82678e00b24044aff8707e/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/4dd4312c4a82678e00b24044aff8707e/output.pkl new file mode 100644 index 0000000..f548504 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/4dd4312c4a82678e00b24044aff8707e/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/61cd7da84c1bbfd3fb974c2dba5bf7df/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/61cd7da84c1bbfd3fb974c2dba5bf7df/output.pkl deleted file mode 100644 index 75e575e..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/61cd7da84c1bbfd3fb974c2dba5bf7df/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/6545b4aa702bac0436d01ec1bfeddd99/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/6545b4aa702bac0436d01ec1bfeddd99/output.pkl new file mode 100644 index 0000000..92b5875 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/6545b4aa702bac0436d01ec1bfeddd99/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/66279ddb5b8d7b05eb2739cbfe061793/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/66279ddb5b8d7b05eb2739cbfe061793/output.pkl new file mode 100644 index 0000000..c3b17a1 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/66279ddb5b8d7b05eb2739cbfe061793/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/6a12ae0f184666fde4be0bcb0b809bc1/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/6a12ae0f184666fde4be0bcb0b809bc1/output.pkl new file mode 100644 index 0000000..8f0be83 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/6a12ae0f184666fde4be0bcb0b809bc1/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/6c2a1b83e6bcde1b3562dd60983bd528/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/6c2a1b83e6bcde1b3562dd60983bd528/metadata.json new file mode 100644 index 0000000..f3c71da --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/6c2a1b83e6bcde1b3562dd60983bd528/metadata.json @@ -0,0 +1 @@ +{"duration": 35.23522090911865, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13 F14 F15 ... F27 F28 F29 F30 F31 F32 F33 F34 F35 F36 F37 F38 F39 F40 F41\n0 1.185 9.085 0 0 2.263 3 0 3.642 0.000 0 1 9.902 46.7 1 3.1934 ... 0 0 2 0 0.000 1 0 0 0.014 0 4.054 0 0 0 0\n1 0.000 8.179 2 0 2.194 0 6 3.526 0.000 6 0 10.054 35.1 0 1.8929 ... 0 0 0 0 0.000 2 0 0 0.000 0 3.489 0 4 0 0\n2 0.762 8.297 0 3 2.424 0 0 3.339 21.884 0 0 10.226 42.1 0 2.3934 ... 0 0 0 8 -0.686 3 0 0 0.004 0 3.693 0 0 0 0\n3 1.747 9.673 0 2 2.690 23 0 4.645 9.855 0 1 12.353 31.6 0 7.7233 ... 1 0 0 2 -4.617 0 0 11 0.000 0 3.993 0 0 0 1\n4 1.824 9.825 0 2 2.700 27 0 4.795 9.894 0 1 12.519 31.8 0 7.9184 ... 1 0 0 2 -4.724 0 0 13 0.000 0 4.005 0 0 0 1\n.. ... ... .. .. ... .. .. ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...\n832 1.125 7.878 0 1 2.136 0 0 2.990 0.000 0 0 9.311 43.8 0 3.0778 ... 0 0 1 2 0.000 1 0 0 0.045 0 3.573 0 0 0 0\n833 1.187 8.046 1 1 2.222 0 2 3.105 0.000 2 0 9.668 38.9 0 3.2726 ... 2 0 2 2 0.000 1 0 0 -0.025 0 3.666 0 2 0 0\n834 0.625 8.901 0 2 2.499 0 0 3.745 24.203 0 0 10.681 58.3 0 2.3715 ... 0 0 0 8 -0.128 6 0 0 0.000 0 3.942 0 0 0 0\n835 3.866 8.778 0 6 2.361 0 0 4.201 11.747 0 1 10.735 32.4 0 1.9452 ... 3 0 0 9 -0.347 1 0 0 0.000 0 3.497 0 0 0 0\n836 3.706 8.680 0 6 2.361 0 0 4.127 11.724 0 1 10.694 31.4 0 1.9472 ... 3 0 0 9 -0.338 1 0 0 0.000 0 3.497 0 0 0 0\n\n[837 rows x 41 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=0.90580836121682,\n eta=0.2665440364437338, gamma=0, gpu_id=-1,\n importance_type='gain', interaction_constraints='',\n learning_rate=0.14016725176148134, max_delta_step=0, max_depth=10,\n min_child_weight=1, missing=nan, monotone_constraints='()',\n n_estimators=108, n_jobs=12, num_parallel_tree=1,\n probability=True, random_state=42, reg_alpha=0, reg_lambda=1,\n scale_pos_weight=1, silent=True, subsample=0.9969909852161994,\n tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/6c4a3c6ccc38028fd8eb8e3cafea6fb8/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/6c4a3c6ccc38028fd8eb8e3cafea6fb8/metadata.json deleted file mode 100644 index f025dba..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/6c4a3c6ccc38028fd8eb8e3cafea6fb8/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 2.988314151763916, "input_args": {"Data": " F1 F2 F3_l10 F4\n0 2.5 3.3 0.298389 6.0\n1 1.9 2.7 0.282605 5.1\n2 2.1 3.0 0.320533 5.9\n3 1.8 2.9 0.298389 5.6\n4 2.2 3.0 0.304254 5.8\n.. ... ... ... ...\n145 0.3 3.0 0.244984 1.4\n146 0.2 3.8 0.257268 1.6\n147 0.2 3.2 0.236226 1.4\n148 0.2 3.7 0.264948 1.5\n149 0.2 3.3 0.253280 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=44.03816499590499, gamma=0.01, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/7316c0ffbde67de29cfaf5cef47b4f6f/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/7316c0ffbde67de29cfaf5cef47b4f6f/output.pkl new file mode 100644 index 0000000..2ccfd22 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/7316c0ffbde67de29cfaf5cef47b4f6f/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/750508bdebd79d7c12403e0a9209597e/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/750508bdebd79d7c12403e0a9209597e/metadata.json new file mode 100644 index 0000000..37c817e --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/750508bdebd79d7c12403e0a9209597e/metadata.json @@ -0,0 +1 @@ +{"duration": 12.906700134277344, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9\n0 7 8 7 8 9 10 10 1 10\n1 4 5 2 3 4 3 3 1 3\n2 5 8 7 10 5 7 5 4 9\n3 3 7 6 4 4 4 6 1 1\n4 1 10 4 6 4 7 7 2 10\n.. .. .. .. .. .. .. .. .. ..\n694 1 1 2 3 1 1 1 1 1\n695 1 3 2 1 1 1 1 1 1\n696 1 3 2 1 2 1 1 2 1\n697 1 3 3 1 1 1 1 1 2\n698 1 2 2 1 1 1 1 1 1\n\n[699 rows x 9 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.0989957156047863,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.0989957154,\n max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=68, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/768047f135420d9d2955707ad2357419/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/768047f135420d9d2955707ad2357419/metadata.json new file mode 100644 index 0000000..915deb5 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/768047f135420d9d2955707ad2357419/metadata.json @@ -0,0 +1 @@ +{"duration": 17.325084924697876, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13\n0 1 0 145 0 150 63 233 1 2.3 0 3 0 1\n1 0 0 130 0 187 37 250 1 3.5 1 2 0 2\n2 0 2 130 0 172 41 204 0 1.4 0 1 0 2\n3 0 2 120 0 178 56 236 1 0.8 1 1 0 2\n4 0 2 120 1 163 57 354 0 0.6 1 0 0 2\n.. .. .. ... .. ... .. ... .. ... ... ... ... ...\n298 0 1 140 1 123 57 241 0 0.2 1 0 0 3\n299 0 1 110 0 132 45 264 1 1.2 1 3 0 3\n300 1 1 144 0 141 68 193 1 3.4 1 0 2 3\n301 0 1 130 1 115 57 131 1 1.2 1 0 1 3\n302 0 1 130 0 174 57 236 0 0.0 0 1 1 2\n\n[303 rows x 13 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17578338868707993,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.175783396,\n max_delta_step=0, max_depth=7, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=183, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/77fea9bd3b261749a4919132a55d4c8b/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/77fea9bd3b261749a4919132a55d4c8b/metadata.json deleted file mode 100644 index fb858dc..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/77fea9bd3b261749a4919132a55d4c8b/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 7.335001707077026, "input_args": {"Data": " F1 F2 F3 F4\n0 2.5 3.3 6.3 6.0\n1 1.9 2.7 5.8 5.1\n2 2.1 3.0 7.1 5.9\n3 1.8 2.9 6.3 5.6\n4 2.2 3.0 6.5 5.8\n.. ... ... ... ...\n145 0.3 3.0 4.8 1.4\n146 0.2 3.8 5.1 1.6\n147 0.2 3.2 4.6 1.4\n148 0.2 3.7 5.3 1.5\n149 0.2 3.3 5.0 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=46.46493418419044, gamma=0.1, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/7b0a5c188fd9aceb09dfd157de9124db/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/7b0a5c188fd9aceb09dfd157de9124db/output.pkl deleted file mode 100644 index d601d91..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/7b0a5c188fd9aceb09dfd157de9124db/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/800d6b604ca72f3d49b1771dd38af263/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/800d6b604ca72f3d49b1771dd38af263/output.pkl new file mode 100644 index 0000000..8669f95 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/800d6b604ca72f3d49b1771dd38af263/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/8169bbe5eb5987ead864ab325567de1e/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/8169bbe5eb5987ead864ab325567de1e/metadata.json new file mode 100644 index 0000000..f9ee41c --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/8169bbe5eb5987ead864ab325567de1e/metadata.json @@ -0,0 +1 @@ +{"duration": 10.679436922073364, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8\n0 72 50 33.6 6 35 0.627 0 148\n1 64 32 23.3 8 0 0.672 0 183\n2 40 33 43.1 0 35 2.288 168 137\n3 50 26 31.0 3 32 0.248 88 78\n4 70 53 30.5 2 45 0.158 543 197\n.. .. .. ... .. .. ... ... ...\n763 62 33 22.5 9 0 0.142 0 89\n764 76 63 32.9 10 48 0.171 180 101\n765 70 27 36.8 2 27 0.340 0 122\n766 72 30 26.2 5 23 0.245 112 121\n767 70 23 30.4 1 31 0.315 0 93\n\n[768 rows x 8 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.2389507198189842,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.238950714,\n max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=17, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/85e0be8fbd7841f797f3bc77720c7db8/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/85e0be8fbd7841f797f3bc77720c7db8/metadata.json new file mode 100644 index 0000000..2f657c4 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/85e0be8fbd7841f797f3bc77720c7db8/metadata.json @@ -0,0 +1 @@ +{"duration": 16.14510416984558, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8\n0 72 50 33.6 6 35 0.627 0 148\n1 64 32 23.3 8 0 0.672 0 183\n2 40 33 43.1 0 35 2.288 168 137\n3 50 26 31.0 3 32 0.248 88 78\n4 70 53 30.5 2 45 0.158 543 197\n... .. .. ... .. .. ... ... ...\n1531 62 33 22.5 9 0 0.142 0 89\n1532 76 63 32.9 10 48 0.171 180 101\n1533 70 27 36.8 2 27 0.340 0 122\n1534 72 30 26.2 5 23 0.245 112 121\n1535 70 23 30.4 1 31 0.315 0 93\n\n[1536 rows x 8 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.1261534422933427,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.126153439,\n max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=138, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/883ab89549bbca0bfafb9f9e5a3e0400/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/883ab89549bbca0bfafb9f9e5a3e0400/output.pkl deleted file mode 100644 index ee077ca..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/883ab89549bbca0bfafb9f9e5a3e0400/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/8acd1de1317c1ff3977e18a58b7d3733/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/8acd1de1317c1ff3977e18a58b7d3733/metadata.json deleted file mode 100644 index 0723e58..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/8acd1de1317c1ff3977e18a58b7d3733/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 3.0411131381988525, "input_args": {"Data": " F1 F2 F3_l1p F4\n0 2.5 3.3 1.987874 6.0\n1 1.9 2.7 1.916923 5.1\n2 2.1 3.0 2.091864 5.9\n3 1.8 2.9 1.987874 5.6\n4 2.2 3.0 2.014903 5.8\n.. ... ... ... ...\n145 0.3 3.0 1.757858 1.4\n146 0.2 3.8 1.808289 1.6\n147 0.2 3.2 1.722767 1.4\n148 0.2 3.7 1.840550 1.5\n149 0.2 3.3 1.791759 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=44.03816499590499, gamma=0.01, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/8d61d1ada863c3928e0b63334ee118b7/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/8d61d1ada863c3928e0b63334ee118b7/output.pkl new file mode 100644 index 0000000..ccaea62 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/8d61d1ada863c3928e0b63334ee118b7/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/8e1aa723d4013c2d967ce085552fa38e/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/8e1aa723d4013c2d967ce085552fa38e/output.pkl new file mode 100644 index 0000000..fbfee23 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/8e1aa723d4013c2d967ce085552fa38e/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/94da8e9a31bea28d8ff8ea53a406d37b/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/94da8e9a31bea28d8ff8ea53a406d37b/metadata.json deleted file mode 100644 index 59577ce..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/94da8e9a31bea28d8ff8ea53a406d37b/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 8.3280029296875, "input_args": {"Data": " F1 F2 F3 F4\n0 2.5 3.3 6.3 6.0\n1 1.9 2.7 5.8 5.1\n2 2.1 3.0 7.1 5.9\n3 1.8 2.9 6.3 5.6\n4 2.2 3.0 6.5 5.8\n.. ... ... ... ...\n145 0.3 3.0 4.8 1.4\n146 0.2 3.8 5.1 1.6\n147 0.2 3.2 4.6 1.4\n148 0.2 3.7 5.3 1.5\n149 0.2 3.3 5.0 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=4.407539756085735, gamma=0.1935853267468035, probability=True,\n random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/9902cbfccf20447a3c3f958bc3ba28f0/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/9902cbfccf20447a3c3f958bc3ba28f0/metadata.json deleted file mode 100644 index cb38325..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/9902cbfccf20447a3c3f958bc3ba28f0/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 5.4526307582855225, "input_args": {"Data": " F1 F2_mms F3 F4\n0 2.5 0.541667 6.3 6.0\n1 1.9 0.291667 5.8 5.1\n2 2.1 0.416667 7.1 5.9\n3 1.8 0.375000 6.3 5.6\n4 2.2 0.416667 6.5 5.8\n.. ... ... ... ...\n145 0.3 0.416667 4.8 1.4\n146 0.2 0.750000 5.1 1.6\n147 0.2 0.500000 4.6 1.4\n148 0.2 0.708333 5.3 1.5\n149 0.2 0.541667 5.0 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=44.03816499590499, gamma=0.01, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/9a08c17b423b35a0c58bb1d4053f6ab9/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/9a08c17b423b35a0c58bb1d4053f6ab9/metadata.json deleted file mode 100644 index b1324f1..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/9a08c17b423b35a0c58bb1d4053f6ab9/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 8.652288913726807, "input_args": {"Data": " F1 F2 F3 F4\n0 2.5 3.3 6.3 6.0\n1 1.9 2.7 5.8 5.1\n2 2.1 3.0 7.1 5.9\n3 1.8 2.9 6.3 5.6\n4 2.2 3.0 6.5 5.8\n.. ... ... ... ...\n145 0.3 3.0 4.8 1.4\n146 0.2 3.8 5.1 1.6\n147 0.2 3.2 4.6 1.4\n148 0.2 3.7 5.3 1.5\n149 0.2 3.3 5.0 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=44.03816499590499, gamma=0.01, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/a42f327147499bdd5ab86868e8668849/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/a42f327147499bdd5ab86868e8668849/metadata.json deleted file mode 100644 index 122b063..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/a42f327147499bdd5ab86868e8668849/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 3.5112879276275635, "input_args": {"Data": " F1 F3 F1+F3 |F1-F3| F1xF3 F1/F3 F3/F1\n0 2.5 6.3 8.8 3.8 15.75 0.396825 2.520000\n1 1.9 5.8 7.7 3.9 11.02 0.327586 3.052632\n2 2.1 7.1 9.2 5.0 14.91 0.295775 3.380952\n3 1.8 6.3 8.1 4.5 11.34 0.285714 3.500000\n4 2.2 6.5 8.7 4.3 14.30 0.338462 2.954545\n.. ... ... ... ... ... ... ...\n145 0.3 4.8 5.1 4.5 1.44 0.062500 16.000000\n146 0.2 5.1 5.3 4.9 1.02 0.039216 25.500000\n147 0.2 4.6 4.8 4.4 0.92 0.043478 23.000000\n148 0.2 5.3 5.5 5.1 1.06 0.037736 26.500000\n149 0.2 5.0 5.2 4.8 1.00 0.040000 25.000000\n\n[150 rows x 7 columns]", "clf": "SVC(C=44.03816499590499, gamma=0.01, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/a6cd214b11321a47cd883aa6152a0c8c/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/a6cd214b11321a47cd883aa6152a0c8c/metadata.json new file mode 100644 index 0000000..aa69953 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/a6cd214b11321a47cd883aa6152a0c8c/metadata.json @@ -0,0 +1 @@ +{"duration": 2.294894218444824, "input_args": {"Data": " F1_p2 F3_em1 F1+F3 |F1-F3| F1xF3 F1/F3 F3/F1\n0 6.25 543.571910 549.821910 537.321910 3397.324438 0.011498 86.971506\n1 3.61 329.299560 332.909560 325.689560 1188.771411 0.010963 91.218715\n2 4.41 1210.967074 1215.377074 1206.557074 5340.364799 0.003642 274.595709\n3 3.24 543.571910 546.811910 540.331910 1761.172989 0.005961 167.769108\n4 4.84 664.141633 668.981633 659.301633 3214.445504 0.007288 137.219346\n.. ... ... ... ... ... ... ...\n145 0.09 120.510418 120.600418 120.420418 10.845938 0.000747 1339.004639\n146 0.04 163.021907 163.061907 162.981907 6.520876 0.000245 4075.547682\n147 0.04 98.484316 98.524316 98.444316 3.939373 0.000406 2462.107891\n148 0.04 199.336810 199.376810 199.296810 7.973472 0.000201 4983.420249\n149 0.04 147.413159 147.453159 147.373159 5.896526 0.000271 3685.328978\n\n[150 rows x 7 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/a963da2af479fc7131606a3122a7d660/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/a963da2af479fc7131606a3122a7d660/output.pkl new file mode 100644 index 0000000..7b83a5a Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/a963da2af479fc7131606a3122a7d660/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/aaec3f41e961d659d743a34d624d2ef2/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/aaec3f41e961d659d743a34d624d2ef2/output.pkl new file mode 100644 index 0000000..1a652c9 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/aaec3f41e961d659d743a34d624d2ef2/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/ac707cf3d91bd14a68c24c11e4b4686b/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/ac707cf3d91bd14a68c24c11e4b4686b/metadata.json new file mode 100644 index 0000000..78fe5d2 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/ac707cf3d91bd14a68c24c11e4b4686b/metadata.json @@ -0,0 +1 @@ +{"duration": 19.514513969421387, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13\n0 1 0 145 0 150 63 233 1 2.3 0 3 0 1\n1 0 0 130 0 187 37 250 1 3.5 1 2 0 2\n2 0 2 130 0 172 41 204 0 1.4 0 1 0 2\n3 0 2 120 0 178 56 236 1 0.8 1 1 0 2\n4 0 2 120 1 163 57 354 0 0.6 1 0 0 2\n.. .. .. ... .. ... .. ... .. ... ... ... ... ...\n298 0 1 140 1 123 57 241 0 0.2 1 0 0 3\n299 0 1 110 0 132 45 264 1 1.2 1 3 0 3\n300 1 1 144 0 141 68 193 1 3.4 1 0 2 3\n301 0 1 130 1 115 57 131 1 1.2 1 0 1 3\n302 0 1 130 0 174 57 236 0 0.0 0 1 1 2\n\n[303 rows x 13 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.13526658776256462,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.135266587,\n max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=231, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/b6980566e56bede9c64acf923379952c/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/b6980566e56bede9c64acf923379952c/output.pkl new file mode 100644 index 0000000..a96682d Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/b6980566e56bede9c64acf923379952c/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/bb0856b15a01508f89cf610063750776/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/bb0856b15a01508f89cf610063750776/output.pkl deleted file mode 100644 index 3ef6690..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/bb0856b15a01508f89cf610063750776/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/bc39a1e21fff991e52cf92f23a887f48/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/bc39a1e21fff991e52cf92f23a887f48/metadata.json new file mode 100644 index 0000000..439f4e4 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/bc39a1e21fff991e52cf92f23a887f48/metadata.json @@ -0,0 +1 @@ +{"duration": 1.298875093460083, "input_args": {"Data": " F1 F2_l1p F3 F4_l2\n0 2.5 1.458615 6.3 2.584963\n1 1.9 1.308333 5.8 2.350497\n2 2.1 1.386294 7.1 2.560715\n3 1.8 1.360977 6.3 2.485427\n4 2.2 1.386294 6.5 2.536053\n.. ... ... ... ...\n145 0.3 1.386294 4.8 0.485427\n146 0.2 1.568616 5.1 0.678072\n147 0.2 1.435085 4.6 0.485427\n148 0.2 1.547563 5.3 0.584963\n149 0.2 1.458615 5.0 0.485427\n\n[150 rows x 4 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/bfc26861bf33c58f2b55e638217c7047/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/bfc26861bf33c58f2b55e638217c7047/output.pkl new file mode 100644 index 0000000..dd155b8 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/bfc26861bf33c58f2b55e638217c7047/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/c01cd11e96d9a10fbadcce2961183ecd/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/c01cd11e96d9a10fbadcce2961183ecd/output.pkl deleted file mode 100644 index d5f72d4..0000000 Binary files a/cachedir/joblib/run/estimatorFeatureSelection/c01cd11e96d9a10fbadcce2961183ecd/output.pkl and /dev/null differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/c4fdd8ce8dd203260a15f6fa9f1fd4fa/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/c4fdd8ce8dd203260a15f6fa9f1fd4fa/output.pkl new file mode 100644 index 0000000..1197ccf Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/c4fdd8ce8dd203260a15f6fa9f1fd4fa/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/c5a7d28fb08d1dd352f1a14ab72c2f82/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/c5a7d28fb08d1dd352f1a14ab72c2f82/metadata.json deleted file mode 100644 index 213f29c..0000000 --- a/cachedir/joblib/run/estimatorFeatureSelection/c5a7d28fb08d1dd352f1a14ab72c2f82/metadata.json +++ /dev/null @@ -1 +0,0 @@ -{"duration": 2.5880067348480225, "input_args": {"Data": " F1 F2 F3_l1p F4\n0 2.5 3.3 1.987874 6.0\n1 1.9 2.7 1.916923 5.1\n2 2.1 3.0 2.091864 5.9\n3 1.8 2.9 1.987874 5.6\n4 2.2 3.0 2.014903 5.8\n.. ... ... ... ...\n145 0.3 3.0 1.757858 1.4\n146 0.2 3.8 1.808289 1.6\n147 0.2 3.2 1.722767 1.4\n148 0.2 3.7 1.840550 1.5\n149 0.2 3.3 1.791759 1.4\n\n[150 rows x 4 columns]", "clf": "SVC(C=46.46493418419044, gamma=0.1, probability=True, random_state=42)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/cb379999e8f23ffa41cf2d9e4bf80e02/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/cb379999e8f23ffa41cf2d9e4bf80e02/metadata.json new file mode 100644 index 0000000..e7aa398 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/cb379999e8f23ffa41cf2d9e4bf80e02/metadata.json @@ -0,0 +1 @@ +{"duration": 9.43068790435791, "input_args": {"Data": " F1 F2 F3 F4\n0 2.5 3.3 6.3 6.0\n1 1.9 2.7 5.8 5.1\n2 2.1 3.0 7.1 5.9\n3 1.8 2.9 6.3 5.6\n4 2.2 3.0 6.5 5.8\n.. ... ... ... ...\n145 0.3 3.0 4.8 1.4\n146 0.2 3.8 5.1 1.6\n147 0.2 3.2 4.6 1.4\n148 0.2 3.7 5.3 1.5\n149 0.2 3.3 5.0 1.4\n\n[150 rows x 4 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/cc4fe1099c6eb367aa1af2b27e92ba46/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/cc4fe1099c6eb367aa1af2b27e92ba46/output.pkl new file mode 100644 index 0000000..6de36fa Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/cc4fe1099c6eb367aa1af2b27e92ba46/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/ce4afe135d18dbc976623139201713b9/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/ce4afe135d18dbc976623139201713b9/metadata.json new file mode 100644 index 0000000..6fdbe77 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/ce4afe135d18dbc976623139201713b9/metadata.json @@ -0,0 +1 @@ +{"duration": 14.877521991729736, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9\n0 7 8 7 8 9 10 10 1 10\n1 4 5 2 3 4 3 3 1 3\n2 5 8 7 10 5 7 5 4 9\n3 3 7 6 4 4 4 6 1 1\n4 1 10 4 6 4 7 7 2 10\n.. .. .. .. .. .. .. .. .. ..\n694 1 1 2 3 1 1 1 1 1\n695 1 3 2 1 1 1 1 1 1\n696 1 3 2 1 2 1 1 2 1\n697 1 3 3 1 1 1 1 1 2\n698 1 2 2 1 1 1 1 1 1\n\n[699 rows x 9 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=0.9597899978811085,\n eta=0.2804685587557792, gamma=0, gpu_id=-1,\n importance_type='gain', interaction_constraints='',\n learning_rate=0.06327387530778793, max_delta_step=0, max_depth=7,\n min_child_weight=1, missing=nan, monotone_constraints='()',\n n_estimators=118, n_jobs=12, num_parallel_tree=1,\n probability=True, random_state=42, reg_alpha=0, reg_lambda=1,\n scale_pos_weight=1, silent=True, subsample=0.9325330330763264,\n tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/cf56b660dce5c9c3345c3e0a4d30aee3/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/cf56b660dce5c9c3345c3e0a4d30aee3/metadata.json new file mode 100644 index 0000000..ad8a9e8 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/cf56b660dce5c9c3345c3e0a4d30aee3/metadata.json @@ -0,0 +1 @@ +{"duration": 4.280111074447632, "input_args": {"Data": " F1 F3 F4\n0 2.5 6.3 6.0\n1 1.9 5.8 5.1\n2 2.1 7.1 5.9\n3 1.8 6.3 5.6\n4 2.2 6.5 5.8\n.. ... ... ...\n145 0.3 4.8 1.4\n146 0.2 5.1 1.6\n147 0.2 4.6 1.4\n148 0.2 5.3 1.5\n149 0.2 5.0 1.4\n\n[150 rows x 3 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/cf635b8f71f7b8fe8d36306657f48f1b/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/cf635b8f71f7b8fe8d36306657f48f1b/output.pkl new file mode 100644 index 0000000..680d7c6 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/cf635b8f71f7b8fe8d36306657f48f1b/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/df2fd4f312f161f0999ac44199d8b992/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/df2fd4f312f161f0999ac44199d8b992/metadata.json new file mode 100644 index 0000000..9131a0a --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/df2fd4f312f161f0999ac44199d8b992/metadata.json @@ -0,0 +1 @@ +{"duration": 17.733853340148926, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13\n0 1 0 145 0 150 63 233 1 2.3 0 3 0 1\n1 0 0 130 0 187 37 250 1 3.5 1 2 0 2\n2 0 2 130 0 172 41 204 0 1.4 0 1 0 2\n3 0 2 120 0 178 56 236 1 0.8 1 1 0 2\n4 0 2 120 1 163 57 354 0 0.6 1 0 0 2\n.. .. .. ... .. ... .. ... .. ... ... ... ... ...\n298 0 1 140 1 123 57 241 0 0.2 1 0 0 3\n299 0 1 110 0 132 45 264 1 1.2 1 3 0 3\n300 1 1 144 0 141 68 193 1 3.4 1 0 2 3\n301 0 1 130 1 115 57 131 1 1.2 1 0 1 3\n302 0 1 130 0 174 57 236 0 0.0 0 1 1 2\n\n[303 rows x 13 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.29618953754932364,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.296189547,\n max_delta_step=0, max_depth=11, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=147, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/dfbd74de0feddbcfb5751ad5fa9a45a6/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/dfbd74de0feddbcfb5751ad5fa9a45a6/output.pkl new file mode 100644 index 0000000..ac5e999 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/dfbd74de0feddbcfb5751ad5fa9a45a6/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/ead41095e08ace486a75207dc8c8e83a/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/ead41095e08ace486a75207dc8c8e83a/output.pkl new file mode 100644 index 0000000..26134f6 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/ead41095e08ace486a75207dc8c8e83a/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/f0cb389e3296abf9505fe1d126fe551a/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/f0cb389e3296abf9505fe1d126fe551a/metadata.json new file mode 100644 index 0000000..bbefc26 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/f0cb389e3296abf9505fe1d126fe551a/metadata.json @@ -0,0 +1 @@ +{"duration": 11.408310174942017, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13 F14 F15 ... F27 F28 F29 F30 F31 F32 F33 F34 F35 F36 F37 F38 F39 F40 F41\n0 1.185 9.085 0 0 2.263 3 0 3.642 0.000 0 1 9.902 46.7 1 3.1934 ... 0 0 2 0 0.000 1 0 0 0.014 0 4.054 0 0 0 0\n1 0.000 8.179 2 0 2.194 0 6 3.526 0.000 6 0 10.054 35.1 0 1.8929 ... 0 0 0 0 0.000 2 0 0 0.000 0 3.489 0 4 0 0\n2 0.762 8.297 0 3 2.424 0 0 3.339 21.884 0 0 10.226 42.1 0 2.3934 ... 0 0 0 8 -0.686 3 0 0 0.004 0 3.693 0 0 0 0\n3 1.747 9.673 0 2 2.690 23 0 4.645 9.855 0 1 12.353 31.6 0 7.7233 ... 1 0 0 2 -4.617 0 0 11 0.000 0 3.993 0 0 0 1\n4 1.824 9.825 0 2 2.700 27 0 4.795 9.894 0 1 12.519 31.8 0 7.9184 ... 1 0 0 2 -4.724 0 0 13 0.000 0 4.005 0 0 0 1\n.. ... ... .. .. ... .. .. ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...\n832 1.125 7.878 0 1 2.136 0 0 2.990 0.000 0 0 9.311 43.8 0 3.0778 ... 0 0 1 2 0.000 1 0 0 0.045 0 3.573 0 0 0 0\n833 1.187 8.046 1 1 2.222 0 2 3.105 0.000 2 0 9.668 38.9 0 3.2726 ... 2 0 2 2 0.000 1 0 0 -0.025 0 3.666 0 2 0 0\n834 0.625 8.901 0 2 2.499 0 0 3.745 24.203 0 0 10.681 58.3 0 2.3715 ... 0 0 0 8 -0.128 6 0 0 0.000 0 3.942 0 0 0 0\n835 3.866 8.778 0 6 2.361 0 0 4.201 11.747 0 1 10.735 32.4 0 1.9452 ... 3 0 0 9 -0.347 1 0 0 0.000 0 3.497 0 0 0 0\n836 3.706 8.680 0 6 2.361 0 0 4.127 11.724 0 1 10.694 31.4 0 1.9472 ... 3 0 0 9 -0.338 1 0 0 0.000 0 3.497 0 0 0 0\n\n[837 rows x 41 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.2581106602001054,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.258110672,\n max_delta_step=0, max_depth=7, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=40, n_jobs=12,\n num_parallel_tree=1, probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=1, silent=True,\n subsample=1, tree_method='exact', use_label_encoder=False,\n validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/f101c13f7a3889fbd799ae832bdaaa8a/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/f101c13f7a3889fbd799ae832bdaaa8a/metadata.json new file mode 100644 index 0000000..5726a1d --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/f101c13f7a3889fbd799ae832bdaaa8a/metadata.json @@ -0,0 +1 @@ +{"duration": 11.91932487487793, "input_args": {"Data": " F1 F2 F3 F4\n0 2.5 3.3 6.3 6.0\n1 1.9 2.7 5.8 5.1\n2 2.1 3.0 7.1 5.9\n3 1.8 2.9 6.3 5.6\n4 2.2 3.0 6.5 5.8\n.. ... ... ... ...\n145 0.3 3.0 4.8 1.4\n146 0.2 3.8 5.1 1.6\n147 0.2 3.2 4.6 1.4\n148 0.2 3.7 5.3 1.5\n149 0.2 3.3 5.0 1.4\n\n[150 rows x 4 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=0.9374540118847363,\n eta=0.28767857660247903, gamma=0, gpu_id=-1,\n importance_type='gain', interaction_constraints='',\n learning_rate=0.15979909127171077, max_delta_step=0, max_depth=9,\n min_child_weight=1, missing=nan, monotone_constraints='()',\n n_estimators=162, n_jobs=12, num_parallel_tree=1,\n objective='multi:softprob', probability=True, random_state=42,\n reg_alpha=0, reg_lambda=1, scale_pos_weight=None, silent=True,\n subsample=0.9155994520336203, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/f9af228a2a31e2aa3608a5268c7e2c6b/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/f9af228a2a31e2aa3608a5268c7e2c6b/metadata.json new file mode 100644 index 0000000..799dc78 --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/f9af228a2a31e2aa3608a5268c7e2c6b/metadata.json @@ -0,0 +1 @@ +{"duration": 10.098360776901245, "input_args": {"Data": " F1 F2 F3 F4 F5 F6 F7 F8\n0 72 50 33.6 6 35 0.627 0 148\n1 64 32 23.3 8 0 0.672 0 183\n2 40 33 43.1 0 35 2.288 168 137\n3 50 26 31.0 3 32 0.248 88 78\n4 70 53 30.5 2 45 0.158 543 197\n.. .. .. ... .. .. ... ... ...\n763 62 33 22.5 9 0 0.142 0 89\n764 76 63 32.9 10 48 0.171 180 101\n765 70 27 36.8 2 27 0.340 0 122\n766 72 30 26.2 5 23 0.245 112 121\n767 70 23 30.4 1 31 0.315 0 93\n\n[768 rows x 8 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.3, gamma=0,\n gpu_id=-1, importance_type='gain', interaction_constraints='',\n learning_rate=0.300000012, max_delta_step=0, max_depth=10,\n min_child_weight=1, missing=nan, monotone_constraints='()',\n n_estimators=15, n_jobs=12, num_parallel_tree=1, probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=1,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, verbosity=0)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/fd4be3fcb80f1a53fcae34da198197cc/metadata.json b/cachedir/joblib/run/estimatorFeatureSelection/fd4be3fcb80f1a53fcae34da198197cc/metadata.json new file mode 100644 index 0000000..5303e6d --- /dev/null +++ b/cachedir/joblib/run/estimatorFeatureSelection/fd4be3fcb80f1a53fcae34da198197cc/metadata.json @@ -0,0 +1 @@ +{"duration": 1.2616550922393799, "input_args": {"Data": " F1_p2 F2_l1p F3 F4_l2\n0 6.25 1.458615 6.3 2.584963\n1 3.61 1.308333 5.8 2.350497\n2 4.41 1.386294 7.1 2.560715\n3 3.24 1.360977 6.3 2.485427\n4 4.84 1.386294 6.5 2.536053\n.. ... ... ... ...\n145 0.09 1.386294 4.8 0.485427\n146 0.04 1.568616 5.1 0.678072\n147 0.04 1.435085 4.6 0.485427\n148 0.04 1.547563 5.3 0.584963\n149 0.04 1.458615 5.0 0.485427\n\n[150 rows x 4 columns]", "clf": "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n colsample_bynode=1, colsample_bytree=1, eta=0.17855860960340292,\n gamma=0, gpu_id=-1, importance_type='gain',\n interaction_constraints='', learning_rate=0.178558603,\n max_delta_step=0, max_depth=9, min_child_weight=1, missing=nan,\n monotone_constraints='()', n_estimators=14, n_jobs=12,\n num_parallel_tree=1, objective='multi:softprob', probability=True,\n random_state=42, reg_alpha=0, reg_lambda=1, scale_pos_weight=None,\n silent=True, subsample=1, tree_method='exact',\n use_label_encoder=False, validate_parameters=1, ...)"}} \ No newline at end of file diff --git a/cachedir/joblib/run/estimatorFeatureSelection/fee13e14d78088e22d8872697a47511a/output.pkl b/cachedir/joblib/run/estimatorFeatureSelection/fee13e14d78088e22d8872697a47511a/output.pkl new file mode 100644 index 0000000..fe3eac6 Binary files /dev/null and b/cachedir/joblib/run/estimatorFeatureSelection/fee13e14d78088e22d8872697a47511a/output.pkl differ diff --git a/cachedir/joblib/run/estimatorFeatureSelection/func_code.py b/cachedir/joblib/run/estimatorFeatureSelection/func_code.py index 18788dc..cda4117 100644 --- a/cachedir/joblib/run/estimatorFeatureSelection/func_code.py +++ b/cachedir/joblib/run/estimatorFeatureSelection/func_code.py @@ -1,4 +1,4 @@ -# first line: 687 +# first line: 693 @memory.cache def estimatorFeatureSelection(Data, clf): @@ -9,15 +9,11 @@ def estimatorFeatureSelection(Data, clf): ImpurityFS = [] RankingFS = [] - rf = RandomForestClassifier(n_estimators = 100, - n_jobs = -1, - random_state = RANDOM_SEED) - rf.fit(Data, yData) + estim = clf.fit(Data, yData) - importances = rf.feature_importances_ - - std = np.std([tree.feature_importances_ for tree in rf.estimators_], - axis=0) + importances = clf.feature_importances_ + # std = np.std([tree.feature_importances_ for tree in estim.feature_importances_], + # axis=0) maxList = max(importances) minList = min(importances) diff --git a/frontend/src/components/DataSetSlider.vue b/frontend/src/components/DataSetSlider.vue index 3d7ec14..d939a0c 100644 --- a/frontend/src/components/DataSetSlider.vue +++ b/frontend/src/components/DataSetSlider.vue @@ -3,8 +3,10 @@ @@ -54,7 +56,7 @@ export default { this.defaultDataSet = fileName.options[fileName.selectedIndex].value this.defaultDataSet = this.defaultDataSet.split('.')[0] - if (this.defaultDataSet == "BiodegC" || this.defaultDataSet == "HeartC" || this.defaultDataSet == "IrisC") { // This is a function that handles a new file, which users can upload. + if (this.defaultDataSet == "BiodegC" || this.defaultDataSet == "HeartC" || this.defaultDataSet == "BreastC" || this.defaultDataSet == "DiabetesC" || this.defaultDataSet == "IrisC") { // This is a function that handles a new file, which users can upload. this.dataset = "Data set" d3.select("#data").select("input").remove(); // Remove the selection field. EventBus.$emit('SendToServerDataSetConfirmation', this.defaultDataSet) diff --git a/frontend/src/components/Main.vue b/frontend/src/components/Main.vue index d0ac0cd..8a7b728 100755 --- a/frontend/src/components/Main.vue +++ b/frontend/src/components/Main.vue @@ -149,7 +149,7 @@ export default Vue.extend({ DataResults: '', keyNow: 1, instancesImportance: '', - RetrieveValueFile: 'IrisC', // this is for the default data set + RetrieveValueFile: 'BreastC', // this is for the default data set SelectedFeaturesPerClassifier: '', FinalResults: 0, selectedAlgorithm: '', @@ -476,7 +476,7 @@ export default Vue.extend({ EventBus.$emit('SlidersCall') this.keySlider = false } - EventBus.$emit('ConfirmDataSet') // REMOVE THAT! + // EventBus.$emit('ConfirmDataSet') // REMOVE THAT! } else { EventBus.$emit('dataSpace', this.correlResul) EventBus.$emit('quad', this.correlResul) diff --git a/insertMongo.py b/insertMongo.py index fffbe5b..d914455 100644 --- a/insertMongo.py +++ b/insertMongo.py @@ -10,7 +10,7 @@ def import_content(filepath): mng_client = pymongo.MongoClient('localhost', 27017) mng_db = mng_client['mydb'] #collection_name = 'StanceCTest' - collection_name = 'StanceC' + collection_name = 'HeartC' db_cm = mng_db[collection_name] cdir = os.path.dirname(__file__) file_res = os.path.join(cdir, filepath) @@ -21,5 +21,5 @@ def import_content(filepath): db_cm.insert(data_json) if __name__ == "__main__": - filepath = '/Users/anchaa/Documents/Research/StackVis_code/StackVis/stance.csv' + filepath = '/Users/anchaa/Documents/Research/FeatureEnVi_code/extra_data_sets/heart.csv' import_content(filepath) \ No newline at end of file diff --git a/run.py b/run.py index 9eb28e9..8af9d14 100644 --- a/run.py +++ b/run.py @@ -14,7 +14,7 @@ import multiprocessing from joblib import Memory -from sklearn.svm import SVC +from xgboost import XGBClassifier from sklearn import model_selection from bayes_opt import BayesianOptimization from sklearn.model_selection import cross_validate @@ -257,7 +257,7 @@ def retrieveFileName(): global listofTransformations listofTransformations = ["r","b","zs","mms","l2","l1p","l10","e2","em1","p2","p3","p4"] - print('data set:',fileName) + DataRawLength = -1 DataRawLengthTest = -1 data = json.loads(fileName) @@ -274,8 +274,10 @@ def retrieveFileName(): target_names.append('Biodegradable') elif data['fileName'] == 'BreastC': CollectionDB = mongo.db.breastC.find() - target_names.append('Malignant') - target_names.append('Benign') + elif data['fileName'] == 'DiabetesC': + CollectionDB = mongo.db.diabetesC.find() + target_names.append('Negative') + target_names.append('Positive') else: CollectionDB = mongo.db.IrisC.find() DataResultsRaw = [] @@ -333,7 +335,7 @@ def sendToServerData(): for i, value in enumerate(AllTargets): if (i == 0): previous = value - if (data['fileName'] == 'IrisC'): + if (data['fileName'] == 'IrisC' or data['fileName'] == 'BreastC'): target_names.append(value) else: pass @@ -341,7 +343,7 @@ def sendToServerData(): AllTargetsFloatValues.append(Class) else: Class = Class + 1 - if (data['fileName'] == 'IrisC'): + if (data['fileName'] == 'IrisC' or data['fileName'] == 'BreastC'): target_names.append(value) else: pass @@ -439,7 +441,7 @@ def dataSetSelection(): for i, value in enumerate(AllTargets): if (i == 0): previous = value - if (data['fileName'] == 'IrisC'): + if (data['fileName'] == 'IrisC' or data['fileName'] == 'BreastC'): target_names.append(value) else: pass @@ -447,7 +449,7 @@ def dataSetSelection(): AllTargetsFloatValues.append(Class) else: Class = Class + 1 - if (data['fileName'] == 'IrisC'): + if (data['fileName'] == 'IrisC' or data['fileName'] == 'BreastC'): target_names.append(value) else: pass @@ -484,9 +486,11 @@ def dataSetSelection(): def create_global_function(): global estimator - def estimator(C, gamma): + def estimator(n_estimators, eta, max_depth): # initialize model - model = SVC(C=C, gamma=gamma, degree=1, random_state=RANDOM_SEED) + n_estimators = int(n_estimators) + max_depth = int(max_depth) + model = XGBClassifier(n_estimators=n_estimators, eta=eta, max_depth=max_depth, n_jobs=-1, random_state=RANDOM_SEED, silent=True, verbosity = 0, use_label_encoder=False) # set in cross-validation result = cross_validate(model, XData, yData, cv=crossValidation, scoring='accuracy') # result is mean of test_score @@ -524,14 +528,14 @@ def executeModel(exeCall, flagEx, nodeTransfName): XData = XDataStored.copy() XDataStoredOriginal = XDataStored.copy() columnsNewGen = keepOriginalFeatures.columns.values.tolist() - # Bayesian Optimization for 50 iterations + # Bayesian Optimization CHANGE INIT_POINTS! if (keyFirstTime): create_global_function() - params = {"C": (0.01, 100), "gamma": (0.01, 100)} - svc_bayesopt = BayesianOptimization(estimator, params, random_state=RANDOM_SEED) - svc_bayesopt.maximize(init_points=30, n_iter=20, acq='ucb') - bestParams = svc_bayesopt.max['params'] - estimator = SVC(C=bestParams.get('C'), gamma=bestParams.get('gamma'), probability=True, random_state=RANDOM_SEED) + params = {"n_estimators": (5, 200), "eta": (0.05, 0.3), "max_depth": (6,12)} + bayesopt = BayesianOptimization(estimator, params, random_state=RANDOM_SEED) + bayesopt.maximize(init_points=35, n_iter=15, acq='ucb') + bestParams = bayesopt.max['params'] + estimator = XGBClassifier(n_estimators=int(bestParams.get('n_estimators')), eta=bestParams.get('eta'), max_depth=int(bestParams.get('max_depth')), probability=True, random_state=RANDOM_SEED, silent=True, verbosity = 0, use_label_encoder=False) if (len(exeCall) != 0): if (flagEx == 1): @@ -580,21 +584,35 @@ def executeModel(exeCall, flagEx, nodeTransfName): elif (splittedCol[1] == 'mms'): XData[nodeTransfName] = (XData[nodeTransfName]-XData[nodeTransfName].min())/(XData[nodeTransfName].max()-XData[nodeTransfName].min()) elif (splittedCol[1] == 'l2'): + dfTemp = [] dfTemp = np.log2(XData[nodeTransfName]) + dfTemp = dfTemp.replace(np.nan, 0) dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) - dfTemp = dfTemp.replace(-np.inf, 2.2250738585072014e-308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) XData[nodeTransfName] = dfTemp elif (splittedCol[1] == 'l1p'): XData[nodeTransfName] = np.log1p(XData[nodeTransfName]) elif (splittedCol[1] == 'l10'): + dfTemp = [] dfTemp = np.log10(XData[nodeTransfName]) + dfTemp = dfTemp.replace(np.nan, 0) dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) - dfTemp = dfTemp.replace(-np.inf, 2.2250738585072014e-308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) XData[nodeTransfName] = dfTemp elif (splittedCol[1] == 'e2'): - XData[nodeTransfName] = np.exp2(XData[nodeTransfName]) + dfTemp = [] + dfTemp = np.exp2(XData[nodeTransfName]) + dfTemp = dfTemp.replace(np.nan, 0) + dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) + XData[nodeTransfName] = dfTemp elif (splittedCol[1] == 'em1'): - XData[nodeTransfName] = np.expm1(XData[nodeTransfName]) + dfTemp = [] + dfTemp = np.expm1(XData[nodeTransfName]) + dfTemp = dfTemp.replace(np.nan, 0) + dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) + XData[nodeTransfName] = dfTemp elif (splittedCol[1] == 'p2'): XData[nodeTransfName] = np.power(XData[nodeTransfName], 2) elif (splittedCol[1] == 'p3'): @@ -620,7 +638,7 @@ def executeModel(exeCall, flagEx, nodeTransfName): estimator.fit(XData, yData) yPredict = estimator.predict(XData) yPredictProb = cross_val_predict(estimator, XData, yData, cv=crossValidation, method='predict_proba') - print(XData) + print('Data set:',XData) num_cores = multiprocessing.cpu_count() inputsSc = ['accuracy','precision_macro','recall_macro'] @@ -636,7 +654,7 @@ def executeModel(exeCall, flagEx, nodeTransfName): if (((scoresAct[0]-scoresAct[1]) + (scoresAct[2]-scoresAct[3]) + (scoresAct[4]-scoresAct[5])) >= ((previousState[0]-previousState[1]) + (previousState[2]-previousState[3]) + (previousState[4]-previousState[5]))): finalResultsData = XData.copy() - print('improved') + print('Improved!') if (keyFirstTime == False): if ((scoresAct[0]-scoresAct[1]) > (previousState[0]-previousState[1])): @@ -694,15 +712,11 @@ def estimatorFeatureSelection(Data, clf): ImpurityFS = [] RankingFS = [] - rf = RandomForestClassifier(n_estimators = 100, - n_jobs = -1, - random_state = RANDOM_SEED) - rf.fit(Data, yData) - - importances = rf.feature_importances_ + estim = clf.fit(Data, yData) - std = np.std([tree.feature_importances_ for tree in rf.estimators_], - axis=0) + importances = clf.feature_importances_ + # std = np.std([tree.feature_importances_ for tree in estim.feature_importances_], + # axis=0) maxList = max(importances) minList = min(importances) @@ -837,32 +851,36 @@ def Transformation(quadrant1, quadrant2, quadrant3, quadrant4, quadrant5): splittedCol = columnsNames[(count)*len(listofTransformations)+0].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf1"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf1"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() XDataNumericCopy[i] = XDataNumericCopy[i].round() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf1"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf1"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+1].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf2"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf2"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() number_of_bins = np.histogram_bin_edges(XDataNumericCopy[i], bins='auto') emptyLabels = [] @@ -877,204 +895,236 @@ def Transformation(quadrant1, quadrant2, quadrant3, quadrant4, quadrant5): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf2"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf2"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+2].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf3"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf3"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() XDataNumericCopy[i] = (XDataNumericCopy[i]-XDataNumericCopy[i].mean())/XDataNumericCopy[i].std() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf3"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf3"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+3].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf4"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf4"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() XDataNumericCopy[i] = (XDataNumericCopy[i]-XDataNumericCopy[i].min())/(XDataNumericCopy[i].max()-XDataNumericCopy[i].min()) for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf4"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf4"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+4].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf5"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf5"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() + dfTemp = [] dfTemp = np.log2(XDataNumericCopy[i]) + dfTemp = dfTemp.replace(np.nan, 0) dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) - dfTemp = dfTemp.replace(-np.inf, 2.2250738585072014e-308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) XDataNumericCopy[i] = dfTemp for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf5"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf5"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+5].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf6"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf6"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() XDataNumericCopy[i] = np.log1p(XDataNumericCopy[i]) for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf6"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf6"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+6].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf7"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf7"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() + dfTemp = [] dfTemp = np.log10(XDataNumericCopy[i]) + dfTemp = dfTemp.replace(np.nan, 0) dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) - dfTemp = dfTemp.replace(-np.inf, 2.2250738585072014e-308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) XDataNumericCopy[i] = dfTemp for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf7"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf7"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+7].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf8"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf8"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() - XDataNumericCopy[i] = np.exp2(XDataNumericCopy[i]) + dfTemp = [] + dfTemp = np.exp2(XDataNumericCopy[i]) + dfTemp = dfTemp.replace(np.nan, 0) + dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) + XDataNumericCopy[i] = dfTemp + if (np.isinf(dfTemp.var())): + flagInf = True for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf8"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf8"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+8].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf9"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf9"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() - XDataNumericCopy[i] = np.expm1(XDataNumericCopy[i]) + dfTemp = [] + dfTemp = np.expm1(XDataNumericCopy[i]) + dfTemp = dfTemp.replace(np.nan, 0) + dfTemp = dfTemp.replace(np.inf, 1.7976931348623157e+308) + dfTemp = dfTemp.replace(-np.inf, 1.7976931348623157e-308) + XDataNumericCopy[i] = dfTemp + if (np.isinf(dfTemp.var())): + flagInf = True for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf9"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf9"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+9].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf10"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf10"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() XDataNumericCopy[i] = np.power(XDataNumericCopy[i], 2) for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf10"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf10"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+10].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf11"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf11"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() XDataNumericCopy[i] = np.power(XDataNumericCopy[i], 3) for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf11"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf11"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) splittedCol = columnsNames[(count)*len(listofTransformations)+11].split('_') if(len(splittedCol) == 1): d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf12"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf12"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) else: d={} + flagInf = False XDataNumericCopy = XDataNumeric.copy() XDataNumericCopy[i] = np.power(XDataNumericCopy[i], 4) for number in range(1,6): quadrantVariable = str('quadrant%s' % number) illusion = locals()[quadrantVariable] d["DataRows{0}".format(number)] = XDataNumericCopy.iloc[illusion, :] - dicTransf["transf12"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count) + dicTransf["transf12"] = NewComputationTransf(d['DataRows1'], d['DataRows2'], d['DataRows3'], d['DataRows4'], d['DataRows5'], quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, i, count, flagInf) packCorrTransformed.append(dicTransf) return 'Everything Okay' -def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, feature, count): - - print(DataRows1) - print(DataRows2) - print(DataRows3) - print(DataRows4) - print(DataRows5) +def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, quadrant1, quadrant2, quadrant3, quadrant4, quadrant5, feature, count, flagInf): corrMatrix1 = DataRows1.corr() corrMatrix1 = corrMatrix1.abs() @@ -1129,9 +1179,12 @@ def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, VIF1 = pd.Series([variance_inflation_factor(X1.values, i) for i in range(X1.shape[1])], index=X1.columns) + VIF1 = VIF1.replace(np.nan, 0) + VIF1 = VIF1.replace(-np.inf, 1.7976931348623157e-308) + VIF1 = VIF1.replace(np.inf, 1.7976931348623157e+308) VIF1 = VIF1.loc[[feature]] - if (len(targetRows1Arr) > 2): - MI1 = mutual_info_classif(DataRows1, targetRows1Arr) + if ((len(targetRows1Arr) > 2) and (flagInf == False)): + MI1 = mutual_info_classif(DataRows1, targetRows1Arr, n_neighbors=3, random_state=RANDOM_SEED) MI1List = MI1.tolist() MI1List = MI1List[count] else: @@ -1154,9 +1207,12 @@ def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, VIF2 = pd.Series([variance_inflation_factor(X2.values, i) for i in range(X2.shape[1])], index=X2.columns) + VIF2 = VIF2.replace(np.nan, 0) + VIF2 = VIF2.replace(-np.inf, 1.7976931348623157e-308) + VIF2 = VIF2.replace(np.inf, 1.7976931348623157e+308) VIF2 = VIF2.loc[[feature]] - if (len(targetRows2Arr) > 2): - MI2 = mutual_info_classif(DataRows2, targetRows2Arr) + if ((len(targetRows2Arr) > 2) and (flagInf == False)): + MI2 = mutual_info_classif(DataRows2, targetRows2Arr, n_neighbors=3, random_state=RANDOM_SEED) MI2List = MI2.tolist() MI2List = MI2List[count] else: @@ -1179,9 +1235,12 @@ def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, VIF3 = pd.Series([variance_inflation_factor(X3.values, i) for i in range(X3.shape[1])], index=X3.columns) + VIF3 = VIF3.replace(np.nan, 0) + VIF3 = VIF3.replace(-np.inf, 1.7976931348623157e-308) + VIF3 = VIF3.replace(np.inf, 1.7976931348623157e+308) VIF3 = VIF3.loc[[feature]] - if (len(targetRows3Arr) > 2): - MI3 = mutual_info_classif(DataRows3, targetRows3Arr) + if ((len(targetRows3Arr) > 2) and (flagInf == False)): + MI3 = mutual_info_classif(DataRows3, targetRows3Arr, n_neighbors=3, random_state=RANDOM_SEED) MI3List = MI3.tolist() MI3List = MI3List[count] else: @@ -1204,9 +1263,12 @@ def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, VIF4 = pd.Series([variance_inflation_factor(X4.values, i) for i in range(X4.shape[1])], index=X4.columns) + VIF4 = VIF4.replace(np.nan, 0) + VIF4 = VIF4.replace(-np.inf, 1.7976931348623157e-308) + VIF4 = VIF4.replace(np.inf, 1.7976931348623157e+308) VIF4 = VIF4.loc[[feature]] - if (len(targetRows4Arr) > 2): - MI4 = mutual_info_classif(DataRows4, targetRows4Arr) + if ((len(targetRows4Arr) > 2) and (flagInf == False)): + MI4 = mutual_info_classif(DataRows4, targetRows4Arr, n_neighbors=3, random_state=RANDOM_SEED) MI4List = MI4.tolist() MI4List = MI4List[count] else: @@ -1229,9 +1291,12 @@ def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, VIF5 = pd.Series([variance_inflation_factor(X5.values, i) for i in range(X5.shape[1])], index=X5.columns) + VIF5 = VIF5.replace(np.nan, 0) + VIF5 = VIF5.replace(-np.inf, 1.7976931348623157e-308) + VIF5 = VIF5.replace(np.inf, 1.7976931348623157e+308) VIF5 = VIF5.loc[[feature]] - if (len(targetRows5Arr) > 2): - MI5 = mutual_info_classif(DataRows5, targetRows5Arr) + if ((len(targetRows5Arr) > 2) and (flagInf == False)): + MI5 = mutual_info_classif(DataRows5, targetRows5Arr, n_neighbors=3, random_state=RANDOM_SEED) MI5List = MI5.tolist() MI5List = MI5List[count] else: @@ -1241,11 +1306,26 @@ def NewComputationTransf(DataRows1, DataRows2, DataRows3, DataRows4, DataRows5, VIF5 = pd.Series() MI5List = [] - corrMatrixComb1 = corrMatrixComb1.loc[[feature]] - corrMatrixComb2 = corrMatrixComb2.loc[[feature]] - corrMatrixComb3 = corrMatrixComb3.loc[[feature]] - corrMatrixComb4 = corrMatrixComb4.loc[[feature]] - corrMatrixComb5 = corrMatrixComb5.loc[[feature]] + if(corrMatrixComb1.empty): + corrMatrixComb1 = pd.DataFrame() + else: + corrMatrixComb1 = corrMatrixComb1.loc[[feature]] + if(corrMatrixComb2.empty): + corrMatrixComb2 = pd.DataFrame() + else: + corrMatrixComb2 = corrMatrixComb2.loc[[feature]] + if(corrMatrixComb3.empty): + corrMatrixComb3 = pd.DataFrame() + else: + corrMatrixComb3 = corrMatrixComb3.loc[[feature]] + if(corrMatrixComb4.empty): + corrMatrixComb4 = pd.DataFrame() + else: + corrMatrixComb4 = corrMatrixComb4.loc[[feature]] + if(corrMatrixComb5.empty): + corrMatrixComb5 = pd.DataFrame() + else: + corrMatrixComb5 = corrMatrixComb5.loc[[feature]] targetRows1ArrDF = pd.DataFrame(targetRows1Arr) targetRows2ArrDF = pd.DataFrame(targetRows2Arr) @@ -1362,6 +1442,7 @@ def Seperation(): DataRows4 = XData.iloc[quadrant4, :] DataRows5 = XData.iloc[quadrant5, :] + Transformation(quadrant1, quadrant2, quadrant3, quadrant4, quadrant5) corrMatrix1 = DataRows1.corr() @@ -1412,8 +1493,11 @@ def Seperation(): VIF1 = pd.Series([variance_inflation_factor(X1.values, i) for i in range(X1.shape[1])], index=X1.columns) + VIF1 = VIF1.replace(np.nan, 0) + VIF1 = VIF1.replace(-np.inf, 1.7976931348623157e-308) + VIF1 = VIF1.replace(np.inf, 1.7976931348623157e+308) if (len(targetRows1Arr) > 2): - MI1 = mutual_info_classif(DataRows1, targetRows1Arr) + MI1 = mutual_info_classif(DataRows1, targetRows1Arr, n_neighbors=3, random_state=RANDOM_SEED) MI1List = MI1.tolist() else: MI1List = [] @@ -1435,8 +1519,11 @@ def Seperation(): VIF2 = pd.Series([variance_inflation_factor(X2.values, i) for i in range(X2.shape[1])], index=X2.columns) + VIF2 = VIF2.replace(np.nan, 0) + VIF2 = VIF2.replace(-np.inf, 1.7976931348623157e-308) + VIF2 = VIF2.replace(np.inf, 1.7976931348623157e+308) if (len(targetRows2Arr) > 2): - MI2 = mutual_info_classif(DataRows2, targetRows2Arr) + MI2 = mutual_info_classif(DataRows2, targetRows2Arr, n_neighbors=3, random_state=RANDOM_SEED) MI2List = MI2.tolist() else: MI2List = [] @@ -1458,8 +1545,11 @@ def Seperation(): VIF3 = pd.Series([variance_inflation_factor(X3.values, i) for i in range(X3.shape[1])], index=X3.columns) + VIF3 = VIF3.replace(np.nan, 0) + VIF3 = VIF3.replace(-np.inf, 1.7976931348623157e-308) + VIF3 = VIF3.replace(np.inf, 1.7976931348623157e+308) if (len(targetRows3Arr) > 2): - MI3 = mutual_info_classif(DataRows3, targetRows3Arr) + MI3 = mutual_info_classif(DataRows3, targetRows3Arr, n_neighbors=3, random_state=RANDOM_SEED) MI3List = MI3.tolist() else: MI3List = [] @@ -1481,8 +1571,11 @@ def Seperation(): VIF4 = pd.Series([variance_inflation_factor(X4.values, i) for i in range(X4.shape[1])], index=X4.columns) + VIF4 = VIF4.replace(np.nan, 0) + VIF4 = VIF4.replace(-np.inf, 1.7976931348623157e-308) + VIF4 = VIF4.replace(np.inf, 1.7976931348623157e+308) if (len(targetRows4Arr) > 2): - MI4 = mutual_info_classif(DataRows4, targetRows4Arr) + MI4 = mutual_info_classif(DataRows4, targetRows4Arr, n_neighbors=3, random_state=RANDOM_SEED) MI4List = MI4.tolist() else: MI4List = [] @@ -1504,8 +1597,11 @@ def Seperation(): VIF5 = pd.Series([variance_inflation_factor(X5.values, i) for i in range(X5.shape[1])], index=X5.columns) + VIF5 = VIF5.replace(np.nan, 0) + VIF5 = VIF5.replace(-np.inf, 1.7976931348623157e-308) + VIF5 = VIF5.replace(np.inf, 1.7976931348623157e+308) if (len(targetRows5Arr) > 2): - MI5 = mutual_info_classif(DataRows5, targetRows5Arr) + MI5 = mutual_info_classif(DataRows5, targetRows5Arr, n_neighbors=3, random_state=RANDOM_SEED) MI5List = MI5.tolist() else: MI5List = []