diff --git a/ProgrammingAssignment_0/GettingFamiliar_solution.ipynb b/ProgrammingAssignment_0/GettingFamiliar_solution.ipynb
index 25d9397e2fea0e0b2630973e837ad802c098f6b6..001ab5a51b5bbe33989c981a809d1ed92488382d 100644
--- a/ProgrammingAssignment_0/GettingFamiliar_solution.ipynb
+++ b/ProgrammingAssignment_0/GettingFamiliar_solution.ipynb
@@ -132,7 +132,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 60,
"metadata": {},
"outputs": [],
"source": [
@@ -179,7 +179,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 61,
"metadata": {},
"outputs": [
{
@@ -214,7 +214,7 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 62,
"metadata": {},
"outputs": [],
"source": [
@@ -276,7 +276,7 @@
},
{
"cell_type": "code",
- "execution_count": 53,
+ "execution_count": 63,
"metadata": {},
"outputs": [
{
@@ -312,7 +312,7 @@
},
{
"cell_type": "code",
- "execution_count": 54,
+ "execution_count": 64,
"metadata": {},
"outputs": [],
"source": [
@@ -351,7 +351,7 @@
},
{
"cell_type": "code",
- "execution_count": 55,
+ "execution_count": 67,
"metadata": {},
"outputs": [
{
@@ -367,7 +367,7 @@
"# obtain features and labels from files\n",
"features, labels = preprocess('../data/madelon.data', '../data/madelon.labels')\n",
"# partition the data set\n",
- "val_indices, test_indices, train_indices = partition(size, 0.3, 0.1)\n",
+ "val_indices, test_indices, train_indices = partition(features.shape[0], 0.3, 0.1)\n",
"# pass the training features and labels to the fit method\n",
"my_model.fit(features[train_indices], labels[train_indices])"
]
diff --git a/ProgrammingAssignment_1/model.ipynb b/ProgrammingAssignment_1/model.ipynb
index 62a4e1553f3b72b3fa3db9b91ef742f7e2a9ed8a..1613f4927df4dd15a3af4f181209ba28e70bc618 100644
--- a/ProgrammingAssignment_1/model.ipynb
+++ b/ProgrammingAssignment_1/model.ipynb
@@ -7,8 +7,8 @@
"# JUPYTER NOTEBOOK TIPS\n",
"\n",
"Each rectangular box is called a cell. \n",
- "* ctrl+ENTER evaluates the current cell; if it contains Python code, it runs the code, if it contains Markdown, it returns rendered text.\n",
- "* alt+ENTER evaluates the current cell and adds a new cell below it.\n",
+ "* Ctrl+ENTER evaluates the current cell; if it contains Python code, it runs the code, if it contains Markdown, it returns rendered text.\n",
+ "* Alt+ENTER evaluates the current cell and adds a new cell below it.\n",
"* If you click to the left of a cell, you'll notice the frame changes color to blue. You can erase a cell by hitting 'dd' (that's two \"d\"s in a row) when the frame is blue."
]
},
@@ -28,23 +28,6 @@
"outputs": [],
"source": [
"class Model:\n",
- " # preprocess_f and partition_f expect functions\n",
- " # use kwargs to pass arguments to preprocessor_f and partition_f\n",
- " # kwargs is a dictionary and should contain t, v, feature_file, label_file\n",
- " # e.g. {'t': 0.3, 'v': 0.1, 'feature_file': 'some_file_name', 'label_file': 'some_file_name'}\n",
- " \n",
- " def __init__(self, preprocessor_f, partition_f, **kwargs):\n",
- " \n",
- " self.features, self.labels = preprocessor_f(kwargs['feature_file'], kwargs['label_file'])\n",
- " self.size = len(self.labels) # number of examples in dataset \n",
- " self.feat_dim = self.features.shape[1] # number of features\n",
- " \n",
- " self.val_indices, self.test_indices = partition_f(self.size, kwargs['t'], kwargs['v'])\n",
- " self.val_size = len(self.val_indices)\n",
- " self.test_size = len(self.test_indices)\n",
- " \n",
- " self.train_indices = np.delete(np.arange(self.size), np.append(self.test_indices, self.val_indices), 0)\n",
- " self.train_size = len(self.train_indices)\n",
" \n",
" def fit(self):\n",
" \n",
@@ -102,7 +85,7 @@
" val_indices: ndarray\n",
" 1D array containing validation set indices\n",
" '''\n",
- " \n",
+ " \n",
" # number of test and validation examples\n",
" t_size = np.int(np.ceil(size*t))\n",
" v_size = np.int(np.ceil(size*v))\n",
@@ -114,9 +97,9 @@
" test_indices = permuted[:t_size]\n",
" # and the next v_size for validation\n",
" val_indices = permuted[t_size+1:t_size+v_size+1]\n",
+ " train_indices = np.delete(np.arange(size), np.append(test_indices, val_indices), 0)\n",
" \n",
- " \n",
- " return test_indices, val_indices"
+ " return test_indices, val_indices, train_indices"
]
},
{
@@ -207,7 +190,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "ROC curves are a good way to visualize sensitivity vs. 1-specificity for varying cut off points. Now, implement a \"ROC\" function that predicts the labels of the test set examples using different *threshold* values in \"predict\" and plot the ROC curve. \"ROC\" takes a list containing different *threshold* parameter values to try and returns two arrays; one where each entry is the sensitivity at a given threshold and the other where entries are 1-specificities."
+ "ROC curves are a good way to visualize sensitivity vs. 1-specificity for varying cut off points. \"ROC\" takes a list containing different *threshold* parameter values to try and returns two arrays; one where each entry is the sensitivity at a given threshold and the other where entries are 1-specificities."
]
},
{
@@ -218,12 +201,13 @@
"source": [
"# TODO: Programming Assignment 1\n",
"\n",
- "def ROC(model, indices, value_list):\n",
+ "def ROC(true_labels, preds, value_list):\n",
" '''\n",
" Args:\n",
- " model: a fitted supervised learning model\n",
- " indices: ndarray\n",
- " 1D array containing indices\n",
+ " true_labels: ndarray\n",
+ " 1D array containing true labels\n",
+ " preds: ndarray\n",
+ " 1D array containing thresholded value (e.g. proportion of positive neighbors in kNN)\n",
" value_list: ndarray\n",
" 1D array containing different threshold values\n",
" Returns:\n",
@@ -233,7 +217,6 @@
" 1D array containing 1-specifities\n",
" '''\n",
" \n",
- " # use predict method to obtain predicted labels at different threshold values\n",
" # use conf_matrix to calculate tp, tn, fp, fn\n",
" # calculate sensitivity, 1-specificity\n",
" # return two arrays\n",
diff --git a/ProgrammingAssignment_1/model_solution.ipynb b/ProgrammingAssignment_1/model_solution.ipynb
index a4582f3c30f305943118e6756d059094d013902c..c2183591492e04492c23080d1f99d853075e7f74 100644
--- a/ProgrammingAssignment_1/model_solution.ipynb
+++ b/ProgrammingAssignment_1/model_solution.ipynb
@@ -7,8 +7,8 @@
"# JUPYTER NOTEBOOK TIPS\n",
"\n",
"Each rectangular box is called a cell. \n",
- "* ctrl+ENTER evaluates the current cell; if it contains Python code, it runs the code, if it contains Markdown, it returns rendered text.\n",
- "* alt+ENTER evaluates the current cell and adds a new cell below it.\n",
+ "* Ctrl+ENTER evaluates the current cell; if it contains Python code, it runs the code, if it contains Markdown, it returns rendered text.\n",
+ "* Alt+ENTER evaluates the current cell and adds a new cell below it.\n",
"* If you click to the left of a cell, you'll notice the frame changes color to blue. You can erase a cell by hitting 'dd' (that's two \"d\"s in a row) when the frame is blue."
]
},
@@ -131,7 +131,7 @@
" y: ndarray\n",
" 1D array containing coordinates for a point\n",
" metric: str\n",
- " Euclidean, Hamming \n",
+ " Euclidean, Manhattan \n",
" Returns:\n",
" dist: float\n",
" '''\n",
@@ -206,7 +206,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "ROC curves are a good way to visualize sensitivity vs. 1-specificity for varying cut off points. Now, implement a \"ROC\" function that predicts the labels of the test set examples using different *threshold* values in \"predict\" and plot the ROC curve. \"ROC\" takes a list containing different *threshold* parameter values to try and returns two arrays; one where each entry is the sensitivity at a given threshold and the other where entries are 1-specificities."
+ "ROC curves are a good way to visualize sensitivity vs. 1-specificity for varying cut off points. \"ROC\" takes a list containing different *threshold* parameter values to try and returns two arrays; one where each entry is the sensitivity at a given threshold and the other where entries are 1-specificities."
]
},
{
@@ -233,7 +233,6 @@
" 1D array containing 1-specifities\n",
" '''\n",
" \n",
- " # use predict method to obtain predicted labels at different threshold values\n",
" # use conf_matrix to calculate tp, tn, fp, fn\n",
" # calculate sensitivity, 1-specificity\n",
" # return two arrays\n",