Skip to content

Commit f381113

Browse files
kmock930kmock930
committed
Refactored codes in Assignment 1 to ensure number of features and columns needed are loaded as required. Added time elapsed logs to debug the issue of long training process.
1 parent f62fb16 commit f381113

File tree

34 files changed

+97
-155
lines changed

34 files changed

+97
-155
lines changed

‎Assignment 1 - Model Comparison/CSI5155 Assignment 1 Evaluation Part - Kelvin Mock 300453668.ipynb‎

Lines changed: 50 additions & 50 deletions
Large diffs are not rendered by default.

‎Assignment 1 - Model Comparison/CSI5155 Assignment 1 Modelling Part- Kelvin Mock 300453668.ipynb‎

Lines changed: 29 additions & 97 deletions
Original file line numberDiff line numberDiff line change
@@ -1678,7 +1678,7 @@
16781678
"name": "stdout",
16791679
"output_type": "stream",
16801680
"text": [
1681-
"{'decision tree': DecisionTreeClassifier(criterion='entropy', splitter='random'), 'random forest': RandomForestClassifier(criterion='entropy'), 'SVM': SVC(), 'gradient boosting': GradientBoostingClassifier(), 'multi-layer perceptron (MLP)': MLPClassifier(hidden_layer_sizes=3769, learning_rate='adaptive', max_iter=500), 'k��nearest neighbour (k-NN) classifier': KNeighborsClassifier(n_jobs=-1, n_neighbors=7, weights='distance')}\n"
1681+
"{'decision tree': DecisionTreeClassifier(criterion='entropy', splitter='random'), 'random forest': RandomForestClassifier(criterion='entropy'), 'SVM': SVC(), 'gradient boosting': GradientBoostingClassifier(), 'multi-layer perceptron (MLP)': MLPClassifier(hidden_layer_sizes=3769, learning_rate='adaptive', max_iter=500), 'k‐nearest neighbour (k-NN) classifier': KNeighborsClassifier(n_jobs=-1, weights='distance')}\n"
16821682
]
16831683
}
16841684
],
@@ -1742,15 +1742,15 @@
17421742
"output_type": "stream",
17431743
"text": [
17441744
"Number of samples in the Chocolate dataset: 1885\n",
1745-
"Number of features in a sample: 13\n",
1745+
"Number of features in a sample: 12\n",
17461746
"Number of Labels in the Chocolate dataset: 1885\n",
17471747
"Unique Labels: ['non-user' 'user']\n"
17481748
]
17491749
}
17501750
],
17511751
"source": [
17521752
"# Convert the dataset to a numpy array\n",
1753-
"np_samples_choco = df_dataset_choco.iloc[:, :-1].to_numpy();\n",
1753+
"np_samples_choco = df_dataset_choco.iloc[:, 1:-1].to_numpy();\n",
17541754
"np_labels_choco = df_dataset_choco.iloc[:,-1].to_numpy();\n",
17551755
"print(\"Number of samples in the Chocolate dataset: \" + str(len(np_samples_choco)));\n",
17561756
"print(\"Number of features in a sample: \" + str(len(np_samples_choco[random.randint(0, len(np_samples_choco)-1)])));\n",
@@ -1768,13 +1768,13 @@
17681768
"name": "stdout",
17691769
"output_type": "stream",
17701770
"text": [
1771-
"Columns for chocolate dataset: ['ID' 'age' 'gender' 'education' 'country' 'ethnicity' 'nscore' 'escore'\n",
1772-
" 'oscore' 'ascore' 'cscore' 'impuslive' 'ss' 'choc']\n"
1771+
"Columns for chocolate dataset: ['age' 'gender' 'education' 'country' 'ethnicity' 'nscore' 'escore'\n",
1772+
" 'oscore' 'ascore' 'cscore' 'impuslive' 'ss']\n"
17731773
]
17741774
}
17751775
],
17761776
"source": [
1777-
"columns_choco = df_dataset_choco.columns.to_numpy();\n",
1777+
"columns_choco = df_dataset_choco.columns.to_numpy()[1:-1];\n",
17781778
"print(f\"Columns for chocolate dataset: {columns_choco}\");"
17791779
]
17801780
},
@@ -1858,7 +1858,7 @@
18581858
"joblib.dump(choco_y_test, constants.choco_dataset + '_test-set_labels.pkl');\n",
18591859
"# Save the columns array\n",
18601860
"# Note: We don't use the first ID column and the last labels column\n",
1861-
"joblib.dump(columns_choco[1:-1], constants.choco_dataset + \"_columns.pkl\");"
1861+
"joblib.dump(columns_choco, constants.choco_dataset + \"_columns.pkl\");"
18621862
]
18631863
},
18641864
{
@@ -1917,7 +1917,7 @@
19171917
},
19181918
{
19191919
"cell_type": "code",
1920-
"execution_count": null,
1920+
"execution_count": 20,
19211921
"id": "59089074",
19221922
"metadata": {},
19231923
"outputs": [],
@@ -1939,40 +1939,14 @@
19391939
"name": "stdout",
19401940
"output_type": "stream",
19411941
"text": [
1942-
"Training all models\n"
1943-
]
1944-
},
1945-
{
1946-
"name": "stderr",
1947-
"output_type": "stream",
1948-
"text": [
1949-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1950-
" warnings.warn(\n",
1951-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1952-
" warnings.warn(\n",
1953-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1954-
" warnings.warn(\n",
1955-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1956-
" warnings.warn(\n",
1957-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1958-
" warnings.warn(\n",
1959-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1960-
" warnings.warn(\n",
1961-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1962-
" warnings.warn(\n",
1963-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1964-
" warnings.warn(\n",
1965-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1966-
" warnings.warn(\n",
1967-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
1968-
" warnings.warn(\n"
1969-
]
1970-
},
1971-
{
1972-
"name": "stdout",
1973-
"output_type": "stream",
1974-
"text": [
1975-
"All models are completely trained.\n"
1942+
"Training all models\n",
1943+
"Completed training decision tree, in 0:00:00.105568s\n",
1944+
"Completed training random forest, in 0:00:05.836123s\n",
1945+
"Completed training SVM, in 0:00:06.196589s\n",
1946+
"Completed training gradient boosting, in 0:00:12.179263s\n",
1947+
"Completed training MLP, in 0:01:06.500467s\n",
1948+
"Completed training KNN, in 0:01:11.832748s\n",
1949+
"All models are completely trained, within 0:01:11.933396s\n"
19761950
]
19771951
}
19781952
],
@@ -2007,7 +1981,7 @@
20071981
"name": "stdout",
20081982
"output_type": "stream",
20091983
"text": [
2010-
"{'decision tree': DecisionTreeClassifier(criterion='entropy', splitter='random'), 'random forest': RandomForestClassifier(criterion='entropy'), 'SVM': SVC(), 'gradient boosting': GradientBoostingClassifier(), 'multi-layer perceptron (MLP)': MLPClassifier(hidden_layer_sizes=3769, learning_rate='adaptive', max_iter=500), 'k‐nearest neighbour (k-NN) classifier': KNeighborsClassifier(n_jobs=-1, n_neighbors=7, weights='distance')}\n"
1984+
"{'decision tree': DecisionTreeClassifier(criterion='entropy', splitter='random'), 'random forest': RandomForestClassifier(criterion='entropy'), 'SVM': SVC(), 'gradient boosting': GradientBoostingClassifier(), 'multi-layer perceptron (MLP)': MLPClassifier(hidden_layer_sizes=3769, learning_rate='adaptive', max_iter=500), 'k‐nearest neighbour (k-NN) classifier': KNeighborsClassifier(n_jobs=-1, weights='distance')}\n"
20111985
]
20121986
}
20131987
],
@@ -2095,13 +2069,13 @@
20952069
"name": "stdout",
20962070
"output_type": "stream",
20972071
"text": [
2098-
"Columns for mushroom dataset: ['ID' 'age' 'gender' 'education' 'country' 'ethnicity' 'nscore' 'escore'\n",
2099-
" 'oscore' 'ascore' 'cscore' 'impuslive' 'ss' 'mushrooms']\n"
2072+
"Columns for mushroom dataset: ['age' 'gender' 'education' 'country' 'ethnicity' 'nscore' 'escore'\n",
2073+
" 'oscore' 'ascore' 'cscore' 'impuslive' 'ss']\n"
21002074
]
21012075
}
21022076
],
21032077
"source": [
2104-
"columns_mush = df_dataset_mushrooms.columns.to_numpy();\n",
2078+
"columns_mush = df_dataset_mushrooms.columns.to_numpy()[1:-1];\n",
21052079
"print(f\"Columns for mushroom dataset: {columns_mush}\");"
21062080
]
21072081
},
@@ -2197,7 +2171,7 @@
21972171
"joblib.dump(mush_y_test, constants.mushrooms_dataset + '_test-set_labels.pkl');\n",
21982172
"# Save the column names\n",
21992173
"# Note: We don't use the first ID column and the last labels column\n",
2200-
"joblib.dump(columns_mush[1:-1], constants.mushrooms_dataset + \"_columns.pkl\");"
2174+
"joblib.dump(columns_mush, constants.mushrooms_dataset + \"_columns.pkl\");"
22012175
]
22022176
},
22032177
{
@@ -2266,56 +2240,14 @@
22662240
"name": "stdout",
22672241
"output_type": "stream",
22682242
"text": [
2269-
"Training all models\n"
2270-
]
2271-
},
2272-
{
2273-
"name": "stderr",
2274-
"output_type": "stream",
2275-
"text": [
2276-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
2277-
" warnings.warn(\n",
2278-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
2279-
" warnings.warn(\n",
2280-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
2281-
" warnings.warn(\n",
2282-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2283-
" warnings.warn(\n",
2284-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2285-
" warnings.warn(\n",
2286-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2287-
" warnings.warn(\n",
2288-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2289-
" warnings.warn(\n",
2290-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2291-
" warnings.warn(\n",
2292-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2293-
" warnings.warn(\n",
2294-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2295-
" warnings.warn(\n",
2296-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2297-
" warnings.warn(\n",
2298-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2299-
" warnings.warn(\n",
2300-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2301-
" warnings.warn(\n",
2302-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2303-
" warnings.warn(\n",
2304-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2305-
" warnings.warn(\n",
2306-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2307-
" warnings.warn(\n",
2308-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2309-
" warnings.warn(\n",
2310-
"c:\\Users\\kelvi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:702: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.\n",
2311-
" warnings.warn(\n"
2312-
]
2313-
},
2314-
{
2315-
"name": "stdout",
2316-
"output_type": "stream",
2317-
"text": [
2318-
"All models are completely trained.\n"
2243+
"Training all models\n",
2244+
"Completed training decision tree, in 0:00:00.060516s\n",
2245+
"Completed training random forest, in 0:00:05.128584s\n",
2246+
"Completed training SVM, in 0:00:07.143005s\n",
2247+
"Completed training gradient boosting, in 0:00:15.253115s\n",
2248+
"Completed training MLP, in 0:02:04.641959s\n",
2249+
"Completed training KNN, in 0:02:06.566441s\n",
2250+
"All models are completely trained, within 0:02:06.704161s\n"
23192251
]
23202252
}
23212253
],

‎Assignment 1 - Model Comparison/choc/Test Set/choc_test-set_samples.pkl‎

-4.91 KB
Binary file not shown.

‎Assignment 1 - Model Comparison/choc/Test Set/choc_test-set_samples_normalized.pkl‎

-4.91 KB
Binary file not shown.

‎Assignment 1 - Model Comparison/choc/Training Set/choc_train-set_samples.pkl‎

-9.81 KB
Binary file not shown.

‎Assignment 1 - Model Comparison/choc/Training Set/choc_train-set_samples_normalized.pkl‎

-9.81 KB
Binary file not shown.

‎Assignment 1 - Model Comparison/choc/posttrained/choc_model_Gradient_Boosting_posttrained.pkl‎

1.36 KB
Binary file not shown.

‎Assignment 1 - Model Comparison/choc/posttrained/choc_model_KNN_posttrained.pkl‎

-20.6 KB
Binary file not shown.

‎Assignment 1 - Model Comparison/choc/posttrained/choc_model_MLP_posttrained.pkl‎

58.7 KB
Binary file not shown.

‎Assignment 1 - Model Comparison/choc/posttrained/choc_model_SVC_RBF_posttrained.pkl‎

-1.27 KB
Binary file not shown.

0 commit comments

Comments
 (0)