diff --git a/ProgrammingAssignment_0/GettingFamiliar_solution.ipynb b/ProgrammingAssignment_0/GettingFamiliar_solution.ipynb
index 272d1d763113a77be1c7c5b1d0cec08c78537167..73b654683801b1f268cdb6f6c3578f9f941d107f 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": 53,
"metadata": {},
"outputs": [],
"source": [
@@ -152,6 +152,9 @@
" # You might find np.genfromtxt useful for reading in the file. Be careful with the file delimiter, \n",
" # e.g. for comma-separated files use delimiter=',' argument.\n",
" \n",
+ " #TODO\n",
+ " \n",
+ " # read in features and labels\n",
" features = np.genfromtxt(feature_file)\n",
" labels = np.genfromtxt(label_file)\n",
" \n",
@@ -176,21 +179,23 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
- "name": "stderr",
+ "name": "stdout",
"output_type": "stream",
"text": [
- "/home/zh/miniconda3/lib/python3.6/site-packages/ipykernel_launcher.py:17: UserWarning: genfromtxt: Empty input file: \"../data/madelon.data\"\n",
- "/home/zh/miniconda3/lib/python3.6/site-packages/ipykernel_launcher.py:18: UserWarning: genfromtxt: Empty input file: \"../data/madelon.labels\"\n"
+ "Shape of features: (2000, 500)\n",
+ "Shape of labels: (2000,)\n"
]
}
],
"source": [
"features, labels = preprocess(feature_file = '../data/madelon.data', label_file = '../data/madelon.labels')\n",
- "# TODO: Output the dimension of both features and labels."
+ "# TODO: Output the dimension of both features and labels.\n",
+ "print('Shape of features: {}'.format(features.shape))\n",
+ "print('Shape of labels: {}'.format(labels.shape))"
]
},
{
@@ -209,7 +214,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
@@ -237,7 +242,18 @@
" \n",
" # TODO\n",
" \n",
- " raise NotImplementedError\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",
+ "\n",
+ " # shuffle the indices\n",
+ " permuted = np.random.permutation(size)\n",
+ " \n",
+ " # spare the first t_size for test\n",
+ " 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",
+ " \n",
" \n",
" return test_indices, val_indices"
]
@@ -260,15 +276,24 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 52,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Test size: 600, validation size: 200\n"
+ ]
+ }
+ ],
"source": [
"# TODO\n",
"# Pass the correct size argument (number of examples in the whole dataset)\n",
- "test_indices, val_indices = partition(size=..., t = 0.3, v = 0.1)\n",
+ "test_indices, val_indices = partition(size = features.shape[0], t = 0.3, v = 0.1)\n",
"\n",
- "# Output the size of both features and labels."
+ "# Output the length of both features and labels.\n",
+ "print('Test size: {}, validation size: {}'.format(test_indices.shape[0], val_indices.shape[0]))"
]
},
{
@@ -287,7 +312,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
@@ -342,15 +367,24 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 23,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "There are 1200 data points in training partition.\n"
+ ]
+ }
+ ],
"source": [
"# TODO\n",
"# pass the correct arguments to preprocessor_f and partition_f\n",
- "kwargs = {'t': 0.3, 'v': 0.1, 'feature_file': ..., 'label_file': ...}\n",
- "my_model = Model(preprocessor_f=..., partition_f=..., **kwargs)\n",
- "# Output size of the training partition"
+ "kwargs = {'t': 0.3, 'v': 0.1, 'feature_file': '../data/madelon.data', 'label_file': '../data/madelon.labels'}\n",
+ "my_model = Model(preprocessor_f=preprocess, partition_f=partition, **kwargs)\n",
+ "# Output size of the training partition\n",
+ "print('There are {} data points in training partition.'.format(my_model.train_size))"
]
},
{
@@ -384,29 +418,55 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 51,
"metadata": {},
"outputs": [],
"source": [
"# TODO\n",
"# args is a placeholder for the parameters of the function\n",
"# Args and Returns are as in \"preprocess\"\n",
- "def normalized_preprocess(args=...):\n",
- " raise NotImplementedError"
+ "def normalized_preprocess(feature_file, label_file):\n",
+ " \n",
+ " # read in features\n",
+ " raw_features = np.genfromtxt(feature_file)\n",
+ " \n",
+ " # initialize an empty ndarray with the shape of raw_features\n",
+ " dims = raw_features.shape\n",
+ " features = np.empty(dims)\n",
+ " \n",
+ " # divide each column with the max value in it\n",
+ " for col in range(dims[1]):\n",
+ " col_values = raw_features[:, col]\n",
+ " max_val = max(col_values)\n",
+ " features[:, col] = col_values/max_val \n",
+ " \n",
+ " # read in labels\n",
+ " labels = np.genfromtxt(label_file)\n",
+ " \n",
+ " return features.T, labels"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 50,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Max value: 1.0, min value: 0.0\n"
+ ]
+ }
+ ],
"source": [
"# TODO\n",
"\n",
- "kwargs = {'t': 0.3, 'v': 0.1, 'feature_file': ..., 'label_file': ...}\n",
- "my_model = Model(preprocessor_f=..., partition_f=..., **kwargs)\n",
+ "kwargs = {'t': 0.3, 'v': 0.1, 'feature_file': '../data/madelon.data', 'label_file': '../data/madelon.labels'}\n",
+ "my_model = Model(preprocessor_f=normalized_preprocess, partition_f=partition, **kwargs)\n",
+ "# Check that the range of each feature in the training set is in range [0, 1]\n",
"\n",
- "# Check that the range of each feature in the training set is in range [0, 1]"
+ "print('Max value: {}, min value: {}'.format(my_model.features.max(), my_model.features.min()))"
]
}
],