727 lines
27 KiB
Plaintext
727 lines
27 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "DB0vv4pBcWu9"
|
|
},
|
|
"source": [
|
|
"# Q3 Using Scikit-Learn"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "GalZFbfhcWvA"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"#export\n",
|
|
"import numpy as np\n",
|
|
"import pandas as pd\n",
|
|
"import time\n",
|
|
"import gc\n",
|
|
"import random\n",
|
|
"from sklearn.model_selection import cross_val_score, GridSearchCV, cross_validate, train_test_split\n",
|
|
"from sklearn.metrics import accuracy_score, classification_report\n",
|
|
"from sklearn.svm import SVC\n",
|
|
"from sklearn.linear_model import LinearRegression\n",
|
|
"from sklearn.neural_network import MLPClassifier\n",
|
|
"from sklearn.ensemble import RandomForestClassifier\n",
|
|
"from sklearn.preprocessing import StandardScaler, normalize\n",
|
|
"from sklearn.decomposition import PCA\n",
|
|
"from sklearn.impute import SimpleImputer"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"%load_ext autoreload\n",
|
|
"%autoreload 2\n",
|
|
"import tests as tests"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "7WLcC3HAlXUF",
|
|
"outputId": "afd04c19-13dd-4044-a352-40ad8c28cec7"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"#export\n",
|
|
"class GaTech():\n",
|
|
" # Change to your GA Tech Username\n",
|
|
" def GTusername(self):\n",
|
|
" gt_username = \"mpearl3\"\n",
|
|
" return gt_username"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Your python version is 3.7.9\n",
|
|
"✅ ALL GOOD\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%run helpers/verify_config.py # verify the environment setup"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "2Z1gV3UlcWvD"
|
|
},
|
|
"source": [
|
|
"# Q3.1 Data Import and Cleansing Setup"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "9VS44b2kcWvE"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"dataAllocation Function Executed\n",
|
|
"trainSets Function Executed\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"#export\n",
|
|
"class Data():\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def dataAllocation(self,path):\n",
|
|
" # TODO: Separate out the x_data and y_data and return each\n",
|
|
" # args: string path for .csv file\n",
|
|
" # return: pandas dataframe, pandas series\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" data = pd.read_csv(path)\n",
|
|
" y_data = data['y']\n",
|
|
" x_data = data[data.columns[~data.columns.isin(['y'])]] \n",
|
|
" # ------------------------------- \n",
|
|
" return x_data,y_data\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def trainSets(self,x_data,y_data):\n",
|
|
" # TODO: Split 70% of the data into training and 30% into test sets. Call them x_train, x_test, y_train and y_test.\n",
|
|
" # Use the train_test_split method in sklearn with the parameter 'shuffle' set to true and the 'random_state' set to 614.\n",
|
|
" # args: pandas dataframe, pandas dataframe\n",
|
|
" # return: pandas dataframe, pandas dataframe, pandas series, pandas series\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" x_train, x_test, y_train, y_test = train_test_split(x_data,y_data,train_size=0.7,shuffle=True,random_state=614)\n",
|
|
" # -------------------------------\n",
|
|
" return x_train, x_test, y_train, y_test\n",
|
|
"\n",
|
|
"##################################################\n",
|
|
"##### Do not add anything below this line ########\n",
|
|
"tests.dataTest(Data)\n",
|
|
"##################################################"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "q09V5Ux5cWvI"
|
|
},
|
|
"source": [
|
|
"# Q3.2 Linear Regression "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "tnHXBF1UcWvJ"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"linearClassifier Function Executed\n",
|
|
"Linear Regression Train Accuracy: 0.7839851024208566\n",
|
|
"Linear Regression Test Accuracy: 0.7316017316017316\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"#export\n",
|
|
"class LinearRegressionModel():\n",
|
|
" \n",
|
|
" # points [2]\n",
|
|
" def linearClassifier(self,x_train, x_test, y_train):\n",
|
|
" # TODO: Create a LinearRegression classifier and train it.\n",
|
|
" # args: pandas dataframe, pandas dataframe, pandas series\n",
|
|
" # return: numpy array, numpy array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" lg = LinearRegression().fit(x_train,y_train)\n",
|
|
" y_predict_train = lg.predict(np.array(x_train))\n",
|
|
" y_predict_test = lg.predict(np.array(x_test)) \n",
|
|
" # -------------------------------\n",
|
|
" return y_predict_train, y_predict_test\n",
|
|
"\n",
|
|
" # points [1]\n",
|
|
" def lgTrainAccuracy(self,y_train,y_predict_train):\n",
|
|
" # TODO: Return accuracy (on the training set) using the accuracy_score method.\n",
|
|
" # Note: Round the output values greater than or equal to 0.5 to 1 and those less than 0.5 to 0. You can use any method that satisfies the requriements.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE \n",
|
|
" y_predict_train = np.where(y_predict_train >= 0.5, 1, 0)\n",
|
|
" train_accuracy = accuracy_score(y_train,y_predict_train)\n",
|
|
" # ------------------------------- \n",
|
|
" return train_accuracy\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def lgTestAccuracy(self,y_test,y_predict_test):\n",
|
|
" # TODO: Return accuracy (on the testing set) using the accuracy_score method.\n",
|
|
" # Note: Round the output values greater than or equal to 0.5 to 1 and those less than 0.5 to 0. You can use any method that satisfies the requriements.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" y_predict_test = np.where(y_predict_test >= 0.5, 1, 0) \n",
|
|
" test_accuracy = accuracy_score(y_test,y_predict_test)\n",
|
|
" # -------------------------------\n",
|
|
" return test_accuracy\n",
|
|
" \n",
|
|
"##################################################\n",
|
|
"##### Do not add anything below this line ########\n",
|
|
"tests.linearTest(Data,LinearRegressionModel)\n",
|
|
"##################################################"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "WbqnCyHAcWvP"
|
|
},
|
|
"source": [
|
|
"# Q3.3 Random Forest Classifier"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "dTtIFJW7cWvQ"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"randomForestClassifier Function Executed\n",
|
|
"Random Forest Train Accuracy: 1.0\n",
|
|
"Random Forest Test Accuracy: 0.7316017316017316\n",
|
|
"Random Forest Feature Importance: [0.07481604 0.25521095 0.08551354 0.07373347 0.0754602 0.1630978\n",
|
|
" 0.12729624 0.14487176]\n",
|
|
"Random Forest Sorted Feature Importance: [3 0 4 2 6 7 5 1]\n",
|
|
"HyperParameterTuning Function Executed\n",
|
|
"Random Forest Best Parameters: {'max_depth': 8, 'n_estimators': 256}\n",
|
|
"Random Forest Best Score: 0.7858255451713395\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"#export\n",
|
|
"class RFClassifier():\n",
|
|
" \n",
|
|
" # points [2]\n",
|
|
" def randomForestClassifier(self,x_train,x_test, y_train):\n",
|
|
" # TODO: Create a RandomForestClassifier and train it. Set Random state to 614.\n",
|
|
" # args: pandas dataframe, pandas dataframe, pandas series\n",
|
|
" # return: RandomForestClassifier object, numpy array, numpy array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" rf_clf = RandomForestClassifier(random_state=614).fit(x_train,y_train)\n",
|
|
" y_predict_train = rf_clf.predict(x_train)\n",
|
|
" y_predict_test = rf_clf.predict(x_test) \n",
|
|
" # -------------------------------\n",
|
|
" return rf_clf,y_predict_train, y_predict_test\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def rfTrainAccuracy(self,y_train,y_predict_train):\n",
|
|
" # TODO: Return accuracy on the training set using the accuracy_score method.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" train_accuracy = accuracy_score(y_train,y_predict_train)\n",
|
|
" # -------------------------------\n",
|
|
" return train_accuracy\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def rfTestAccuracy(self,y_test,y_predict_test):\n",
|
|
" # TODO: Return accuracy on the test set using the accuracy_score method.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" test_accuracy = accuracy_score(y_test,y_predict_test)\n",
|
|
" # -------------------------------\n",
|
|
" return test_accuracy\n",
|
|
" \n",
|
|
"# Q3.3.1 Feature Importance\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def rfFeatureImportance(self,rf_clf):\n",
|
|
" # TODO: Determine the feature importance as evaluated by the Random Forest Classifier.\n",
|
|
" # args: RandomForestClassifier object\n",
|
|
" # return: float array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" feature_importance = rf_clf.feature_importances_\n",
|
|
" # -------------------------------\n",
|
|
" return feature_importance\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def sortedRFFeatureImportanceIndicies(self,rf_clf):\n",
|
|
" # TODO: Sort them in the descending order and return the feature numbers[0 to ...].\n",
|
|
" # Hint: There is a direct function available in sklearn to achieve this. Also checkout argsort() function in Python.\n",
|
|
" # args: RandomForestClassifier object\n",
|
|
" # return: int array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" sorted_indices = rf_clf.feature_importances_.argsort()\n",
|
|
" # -------------------------------\n",
|
|
" return sorted_indices\n",
|
|
" \n",
|
|
"# Q3.3.2 Hyper-parameter Tuning\n",
|
|
"\n",
|
|
" # points [2]\n",
|
|
" def hyperParameterTuning(self,rf_clf,x_train,y_train):\n",
|
|
" # TODO: Tune the hyper-parameters 'n_estimators' and 'max_depth'.\n",
|
|
" # args: RandomForestClassifier object, pandas dataframe, pandas series\n",
|
|
" # return: GridSearchCV object\n",
|
|
" # 'n_estimators': [4, 16, 256]\n",
|
|
" # 'max_depth': [2, 8, 16]\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" param_grid = {\n",
|
|
" 'n_estimators': [4, 16, 256],\n",
|
|
" 'max_depth': [2, 8, 16]\n",
|
|
" }\n",
|
|
" grid_search = GridSearchCV(estimator = rf_clf, param_grid = param_grid, n_jobs = -1)\n",
|
|
" gscv_rfc = grid_search.fit(x_train,y_train) \n",
|
|
" # -------------------------------\n",
|
|
" return gscv_rfc\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def bestParams(self,gscv_rfc):\n",
|
|
" # TODO: Get the best params, using .best_params_\n",
|
|
" # args: GridSearchCV object\n",
|
|
" # return: parameter dict\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" best_params = gscv_rfc.best_params_\n",
|
|
" # -------------------------------\n",
|
|
" return best_params\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def bestScore(self,gscv_rfc):\n",
|
|
" # TODO: Get the best score, using .best_score_.\n",
|
|
" # args: GridSearchCV object\n",
|
|
" # return: float\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" best_score = gscv_rfc.best_score_\n",
|
|
" # -------------------------------\n",
|
|
" return best_score\n",
|
|
" \n",
|
|
"##################################################\n",
|
|
"##### Do not add anything below this line ########\n",
|
|
"tests.RandomForestTest(Data,RFClassifier)\n",
|
|
"##################################################"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "BNeOPWIpcWvg"
|
|
},
|
|
"source": [
|
|
"# Q3.4 Support Vector Machine"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "9msZXyImcWvh"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" 0 1 2 3 4 5 6 \\\n",
|
|
"0 -1.131241 1.759569 1.067761 0.372070 -0.717966 1.481755 0.645836 \n",
|
|
"1 -0.832433 -3.731472 -0.064501 0.877898 -0.717966 -0.051000 -0.245593 \n",
|
|
"2 0.063991 0.471168 0.758963 -1.335097 -0.717966 -0.152339 -0.656791 \n",
|
|
"3 0.960414 -0.479794 1.170694 -0.196985 -0.717966 -1.229067 -0.707815 \n",
|
|
"4 0.661606 -0.541147 0.244298 -0.196985 0.639076 -0.317015 0.753887 \n",
|
|
".. ... ... ... ... ... ... ... \n",
|
|
"532 -0.533625 -0.694528 -3.564220 -1.335097 -0.717966 -1.292404 -1.088998 \n",
|
|
"533 -0.234817 2.189036 0.038432 0.624984 -0.717966 0.316355 -0.689806 \n",
|
|
"534 -1.131241 0.287111 -0.167434 1.194040 -0.717966 0.240350 -0.824871 \n",
|
|
"535 1.259222 -0.663851 0.244298 1.194040 1.152316 0.886387 0.570799 \n",
|
|
"536 -1.131241 -0.817232 0.810429 0.245613 -0.404803 0.633039 -0.671798 \n",
|
|
"\n",
|
|
" 7 \n",
|
|
"0 -0.867083 \n",
|
|
"1 -0.953726 \n",
|
|
"2 -0.260577 \n",
|
|
"3 1.299010 \n",
|
|
"4 0.692504 \n",
|
|
".. ... \n",
|
|
"532 -0.867083 \n",
|
|
"533 -0.693795 \n",
|
|
"534 -0.953726 \n",
|
|
"535 0.865792 \n",
|
|
"536 -0.780439 \n",
|
|
"\n",
|
|
"[537 rows x 8 columns]\n",
|
|
"dataPreProcess Function Executed\n",
|
|
"SVCClassifier Function Executed\n",
|
|
"Support Vector Machine Trian Accuracy: 0.8324022346368715\n",
|
|
"Support Vector Machine Test Accuracy: 0.7272727272727273\n",
|
|
"0.7820526133610246\n",
|
|
"Support Vector Machine Best Score: 0.7820526133610246\n",
|
|
"SVCClassifierParam Function Executed\n",
|
|
"Support Vector Machine Trian Accuracy: 0.7877094972067039\n",
|
|
"Support Vector Machine Test Accuracy: 0.7575757575757576\n",
|
|
"Support Vector Machine Rank Test Score: [4 6 2 5 1 3]\n",
|
|
"Support Vector Machine Mean Test Score: [0.77826237 0.63501211 0.782018 0.76341295 0.78205261 0.78033922]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"#export\n",
|
|
"class SupportVectorMachine():\n",
|
|
" \n",
|
|
"# Q3.4.1 Pre-process\n",
|
|
"\n",
|
|
" # points [1]\n",
|
|
" def dataPreProcess(self,x_train,x_test):\n",
|
|
" # TODO: Pre-process the data to standardize it, otherwise the grid search will take much longer.\n",
|
|
" # args: pandas dataframe, pandas dataframe\n",
|
|
" # return: pandas dataframe, pandas dataframe\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" sc = StandardScaler()\n",
|
|
" scaled_x_train = pd.DataFrame(sc.fit_transform(x_train))\n",
|
|
" print(scaled_x_train)\n",
|
|
" scaled_x_test = sc.transform(x_test) \n",
|
|
" # -------------------------------\n",
|
|
" return scaled_x_train, scaled_x_test\n",
|
|
" \n",
|
|
"# Q3.4.2 Classification\n",
|
|
"\n",
|
|
" # points [1]\n",
|
|
" def SVCClassifier(self,scaled_x_train,scaled_x_test, y_train):\n",
|
|
" # TODO: Create a SVC classifier and train it. Set gamma = 'auto'\n",
|
|
" # args: pandas dataframe, pandas dataframe, pandas series\n",
|
|
" # return: numpy array, numpy array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" svc = SVC(gamma='auto').fit(scaled_x_train,y_train)\n",
|
|
" y_predict_train = svc.predict(scaled_x_train)\n",
|
|
" y_predict_test = svc.predict(scaled_x_test) \n",
|
|
" # -------------------------------\n",
|
|
" return y_predict_train,y_predict_test\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def SVCTrainAccuracy(self,y_train,y_predict_train):\n",
|
|
" # TODO: Return accuracy on the training set using the accuracy_score method.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float \n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" train_accuracy = accuracy_score(y_train,y_predict_train)\n",
|
|
" # -------------------------------\n",
|
|
" return train_accuracy\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def SVCTestAccuracy(self,y_test,y_predict_test):\n",
|
|
" # TODO: Return accuracy on the test set using the accuracy_score method.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float \n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" test_accuracy = accuracy_score(y_test,y_predict_test)\n",
|
|
" # -------------------------------\n",
|
|
" return test_accuracy\n",
|
|
" \n",
|
|
"# Q3.4.3 Hyper-parameter Tuning\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def SVMBestScore(self, scaled_x_train, y_train):\n",
|
|
" # TODO: Tune the hyper-parameters 'C' and 'kernel' (use rbf and linear).\n",
|
|
" # Note: Set n_jobs = -1 and return_train_score = True and gamma = 'auto'\n",
|
|
" # args: pandas dataframe, pandas series\n",
|
|
" # return: GridSearchCV object, float\n",
|
|
" # -------------------------------\n",
|
|
" svm_parameters = {'kernel':('linear', 'rbf'), 'C':[0.01, 0.1, 1.0]}\n",
|
|
" # ADD CODE HERE\n",
|
|
" svm_new = SVC(gamma='auto')\n",
|
|
" svm_cv = GridSearchCV(estimator = svm_new, param_grid = svm_parameters, n_jobs = -1, return_train_score=True)\n",
|
|
" svm_fit = svm_cv.fit(scaled_x_train, y_train)\n",
|
|
" best_score = svm_fit.best_score_ \n",
|
|
" print(best_score)\n",
|
|
" # -------------------------------\n",
|
|
" \n",
|
|
" return svm_cv, best_score\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def SVCClassifierParam(self,svm_cv,scaled_x_train,scaled_x_test,y_train):\n",
|
|
" # TODO: Calculate the training and test set accuracy values after hyperparameter tuning and standardization. \n",
|
|
" # args: GridSearchCV object, pandas dataframe, pandas dataframe, pandas series\n",
|
|
" # return: numpy series, numpy series\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" y_predict_train = svm_cv.predict(scaled_x_train)\n",
|
|
" y_predict_test = svm_cv.predict(scaled_x_test) \n",
|
|
" # -------------------------------\n",
|
|
" return y_predict_train,y_predict_test\n",
|
|
"\n",
|
|
" # points [1]\n",
|
|
" def svcTrainAccuracy(self,y_train,y_predict_train):\n",
|
|
" # TODO: Return accuracy (on the training set) using the accuracy_score method.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" train_accuracy = accuracy_score(y_train,y_predict_train)\n",
|
|
" # -------------------------------\n",
|
|
" return train_accuracy\n",
|
|
"\n",
|
|
" # points [1]\n",
|
|
" def svcTestAccuracy(self,y_test,y_predict_test):\n",
|
|
" # TODO: Return accuracy (on the test set) using the accuracy_score method.\n",
|
|
" # args: pandas series, numpy array\n",
|
|
" # return: float\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" test_accuracy = accuracy_score(y_test,y_predict_test)\n",
|
|
" # -------------------------------\n",
|
|
" return test_accuracy\n",
|
|
" \n",
|
|
"# Q3.4.4 Cross Validation Results\n",
|
|
"\n",
|
|
" # points [1]\n",
|
|
" def SVMRankTestScore(self,svm_cv):\n",
|
|
" # TODO: Return the rank test score for all hyperparameter values that you obtained in Q3.4.3. The \n",
|
|
" # GridSearchCV class holds a 'cv_results_' dictionary that should help you report these metrics easily.\n",
|
|
" # args: GridSearchCV object \n",
|
|
" # return: int array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" rank_test_score = svm_cv.cv_results_['rank_test_score']\n",
|
|
" # -------------------------------\n",
|
|
" return rank_test_score\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def SVMMeanTestScore(self,svm_cv):\n",
|
|
" # TODO: Return mean test score for all of hyperparameter values that you obtained in Q3.4.3. The \n",
|
|
" # GridSearchCV class holds a 'cv_results_' dictionary that should help you report these metrics easily.\n",
|
|
" # args: GridSearchCV object\n",
|
|
" # return: float array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" mean_test_score = svm_cv.cv_results_['mean_test_score']\n",
|
|
" # -------------------------------\n",
|
|
" return mean_test_score\n",
|
|
"\n",
|
|
"##################################################\n",
|
|
"##### Do not add anything below this line ########\n",
|
|
"tests.SupportVectorMachineTest(Data,SupportVectorMachine)\n",
|
|
"##################################################"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text",
|
|
"id": "c2qDYMjgcWv5"
|
|
},
|
|
"source": [
|
|
"# Q3.5 PCA"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {
|
|
"colab": {},
|
|
"colab_type": "code",
|
|
"id": "-C9BuGsqcWv5"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"pcaClassifier Function Executed\n",
|
|
"PCA Explained Variance Ratio: [8.88546635e-01 6.15907837e-02 2.57901189e-02 1.30861374e-02\n",
|
|
" 7.44093864e-03 3.02614919e-03 5.12444875e-04 6.79264301e-06]\n",
|
|
"PCA Singular Values: [3212.6611207 845.82919167 547.33280231 389.87962763 293.9941346\n",
|
|
" 187.48648707 77.15221185 8.88268374]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"#export\n",
|
|
"class PCAClassifier():\n",
|
|
" \n",
|
|
" # points [2]\n",
|
|
" def pcaClassifier(self,x_data):\n",
|
|
" # TODO: Perform dimensionality reduction of the data using PCA.\n",
|
|
" # Set parameters n_components to 8 and svd_solver to 'full'. Keep other parameters at their default value.\n",
|
|
" # args: pandas dataframe\n",
|
|
" # return: pca_object\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" pca = PCA(n_components=8,svd_solver='full')\n",
|
|
" pca= pca.fit(x_data) \n",
|
|
" # -------------------------------\n",
|
|
" return pca\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def pcaExplainedVarianceRatio(self, pca):\n",
|
|
" # TODO: Return percentage of variance explained by each of the selected components\n",
|
|
" # args: pca_object\n",
|
|
" # return: float array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" explained_variance_ratio = pca.explained_variance_ratio_\n",
|
|
" # -------------------------------\n",
|
|
" return explained_variance_ratio\n",
|
|
" \n",
|
|
" # points [1]\n",
|
|
" def pcaSingularValues(self, pca):\n",
|
|
" # TODO: Return the singular values corresponding to each of the selected components.\n",
|
|
" # args: pca_object\n",
|
|
" # return: float array\n",
|
|
" # -------------------------------\n",
|
|
" # ADD CODE HERE\n",
|
|
" singular_values= pca.singular_values_\n",
|
|
" # -------------------------------\n",
|
|
" return singular_values\n",
|
|
" \n",
|
|
"##################################################\n",
|
|
"##### Do not add anything below this line ########\n",
|
|
"tests.PCATest(Data,PCAClassifier)\n",
|
|
"##################################################"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Late Policy:\n",
|
|
" \n",
|
|
" \"I have read the late policy for CS6424.\"\n",
|
|
" \n",
|
|
"\n",
|
|
"\n",
|
|
"Honor Pledge:\n",
|
|
" \n",
|
|
" \"I have read the Collaboration and Academic Honesty policy for CS6424.\n",
|
|
" I certify that I have or will use outside references only in accordance with\n",
|
|
" this policy, that I have or will cite any such references via code comments,\n",
|
|
" and that I have not or will not copy any portion of my submission from another\n",
|
|
" past or current student.\"\n",
|
|
"\n",
|
|
" \n",
|
|
"\n",
|
|
"\n",
|
|
"Converted Q3.ipynb to submission\\submission.py\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
" %run helpers/notebook2script submission"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"colab": {
|
|
"name": "hw4q3.soln.ipynb",
|
|
"provenance": []
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.7.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 1
|
|
}
|