diff --git a/your-code/bonus.ipynb b/your-code/bonus.ipynb index 92e4a72..8908693 100644 --- a/your-code/bonus.ipynb +++ b/your-code/bonus.ipynb @@ -144,9 +144,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.8.3" } }, "nbformat": 4, - "nbformat_minor": 2 + "nbformat_minor": 4 } diff --git a/your-code/challenge-1.ipynb b/your-code/challenge-1.ipynb index 2487c5f..8770c84 100644 --- a/your-code/challenge-1.ipynb +++ b/your-code/challenge-1.ipynb @@ -34,11 +34,539 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TLTMTRMLMMMRBLBMBRclass
0xxxxooxooTrue
1xxxxoooxoTrue
2xxxxooooxTrue
3xxxxooobbTrue
4xxxxoobobTrue
\n", + "
" + ], + "text/plain": [ + " TL TM TR ML MM MR BL BM BR class\n", + "0 x x x x o o x o o True\n", + "1 x x x x o o o x o True\n", + "2 x x x x o o o o x True\n", + "3 x x x x o o o b b True\n", + "4 x x x x o o b o b True" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd \n", + "tic_tac_toe = pd.read_csv('tic-tac-toe.csv')\n", + "tic_tac_toe.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(958, 10)" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tic_tac_toe.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tic_tac_toe.describe" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "TL object\n", + "TM object\n", + "TR object\n", + "ML object\n", + "MM object\n", + "MR object\n", + "BL object\n", + "BM object\n", + "BR object\n", + "class bool\n", + "dtype: object" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tic_tac_toe.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": {}, + "outputs": [], + "source": [ + "df = pd.DataFrame(tic_tac_toe)" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TLTMTRMLMMMRBLBMBRclass
288200121122True
234202112012True
549012101222True
217210021212True
126212121122True
\n", + "
" + ], + "text/plain": [ + " TL TM TR ML MM MR BL BM BR class\n", + "288 2 0 0 1 2 1 1 2 2 True\n", + "234 2 0 2 1 1 2 0 1 2 True\n", + "549 0 1 2 1 0 1 2 2 2 True\n", + "217 2 1 0 0 2 1 2 1 2 True\n", + "126 2 1 2 1 2 1 1 2 2 True" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.sample(5)" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['TL', 'TM', 'TR', 'ML', 'MM', 'MR', 'BL', 'BM', 'BR', 'class'], dtype='object')" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": {}, + "outputs": [], + "source": [ + "X = df[['TL', 'TM', 'TR', 'ML', 'MM', 'MR', 'BL', 'BM', 'BR']]\n", + "y = df['class']" + ] + }, + { + "cell_type": "code", + "execution_count": 47, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "from sklearn import preprocessing \n", + "label = preprocessing.LabelEncoder()\n", + "\n", + "# Assigning numerical values to the DataFrame \n", + "for x in X:\n", + " label.fit(df[x])\n", + " df[x] = label.transform(df[x])" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TLTMTRMLMMMRBLBMBRclass
0222211211True
1222211121True
2222211112True
3222211100True
4222211010True
\n", + "
" + ], + "text/plain": [ + " TL TM TR ML MM MR BL BM BR class\n", + "0 2 2 2 2 1 1 2 1 1 True\n", + "1 2 2 2 2 1 1 1 2 1 True\n", + "2 2 2 2 2 1 1 1 1 2 True\n", + "3 2 2 2 2 1 1 1 0 0 True\n", + "4 2 2 2 2 1 1 0 1 0 True" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": {}, + "outputs": [], + "source": [ + "#df = pd.get_dummies(tic_tac_toe, columns = ['class'])" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [], + "source": [ + "# Applying standardization to my dataset\n", + "mm_scaler = preprocessing.StandardScaler()\n", + "X = mm_scaler.fit_transform(X)" ] }, { @@ -60,11 +588,194 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 50, + "metadata": {}, + "outputs": [], + "source": [ + "#Split the training and test data.\n", + "\n", + "from sklearn.model_selection import train_test_split\n", + "\n", + "X_train, X_test, y_train, y_test = train_test_split(X,y, random_state = 0)\n", + "\n", + "X_train = mm_scaler.fit_transform(X_train)\n", + "X_test = mm_scaler.transform(X_test)" + ] + }, + { + "cell_type": "code", + "execution_count": 51, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "#Create a Sequential model.\n", + "from sklearn.neural_network import MLPClassifier\n", + "mlp = MLPClassifier(hidden_layer_sizes= (100,200) ,max_iter=20, alpha=1e-4,\n", + " solver='sgd', verbose=10, random_state=1,\n", + " learning_rate_init=.1)\n", + "\n", + "#Add several layers to your model. \n", + "#Make sure you use ReLU as the activation function for the middle layers. \n", + "#Use Softmax for the output layer because each output has a\n", + "#single lable and all the label probabilities add up to 1.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 152, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Iteration 1, loss = 0.66827589\n", + "Iteration 2, loss = 0.62438257\n", + "Iteration 3, loss = 0.58806163\n", + "Iteration 4, loss = 0.56598247\n", + "Iteration 5, loss = 0.54282279\n", + "Iteration 6, loss = 0.52110810\n", + "Iteration 7, loss = 0.49368803\n", + "Iteration 8, loss = 0.46570875\n", + "Iteration 9, loss = 0.43649043\n", + "Iteration 10, loss = 0.40478960\n", + "Iteration 11, loss = 0.37263589\n", + "Iteration 12, loss = 0.34475488\n", + "Iteration 13, loss = 0.31672139\n", + "Iteration 14, loss = 0.29666126\n", + "Iteration 15, loss = 0.27633654\n", + "Iteration 16, loss = 0.26303131\n", + "Iteration 17, loss = 0.24032215\n", + "Iteration 18, loss = 0.21942277\n", + "Iteration 19, loss = 0.20499752\n", + "Iteration 20, loss = 0.18970273\n", + "Training set score: 0.938719\n", + "Test set score: 0.845833\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/jossuebangos/opt/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py:614: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (20) reached and the optimization hasn't converged yet.\n", + " warnings.warn(\n" + ] + } + ], + "source": [ + "mlp.fit(X_train, y_train)\n", + "\n", + "print(\"Training set score: %f\" % mlp.score(X_train, y_train))\n", + "print(\"Test set score: %f\" % mlp.score(X_test, y_test))\n", + "\n", + "# The loss is an estimation of the error in current iteration of the model\n", + "# This model optimizes the log-loss function using LBFGS or stochastic" + ] + }, + { + "cell_type": "code", + "execution_count": 153, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
class
0True
1True
2True
3True
4True
......
953False
954False
955False
956False
957False
\n", + "

958 rows × 1 columns

\n", + "
" + ], + "text/plain": [ + " class\n", + "0 True\n", + "1 True\n", + "2 True\n", + "3 True\n", + "4 True\n", + ".. ...\n", + "953 False\n", + "954 False\n", + "955 False\n", + "956 False\n", + "957 False\n", + "\n", + "[958 rows x 1 columns]" + ] + }, + "execution_count": 153, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "testing_y_real = pd.DataFrame(y)\n", + "testing_y_real" ] }, { @@ -76,13 +787,51 @@ "Now load your saved model and use it to make predictions on a few random rows in the test dataset. Check if the predictions are correct." ] }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [], + "source": [ + "import tensorflow.keras as keras\n", + "import tensorflow as tf" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "ename": "NotFittedError", + "evalue": "This MLPClassifier instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator.", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNotFittedError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m#Make Predictionn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mpredictions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmlp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;36m100\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mtesting_y_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpredictions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mtest\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/sklearn/neural_network/_multilayer_perceptron.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, X)\u001b[0m\n\u001b[1;32m 1031\u001b[0m \u001b[0mThe\u001b[0m \u001b[0mpredicted\u001b[0m \u001b[0mclasses\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1032\u001b[0m \"\"\"\n\u001b[0;32m-> 1033\u001b[0;31m \u001b[0mcheck_is_fitted\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1034\u001b[0m \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_forward_pass_fast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1035\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36minner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 63\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 64\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 65\u001b[0m \u001b[0;31m# extra_args > 0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36mcheck_is_fitted\u001b[0;34m(estimator, attributes, msg, all_or_any)\u001b[0m\n\u001b[1;32m 1039\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1040\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mattrs\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1041\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mNotFittedError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m'name'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mestimator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1042\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1043\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mNotFittedError\u001b[0m: This MLPClassifier instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator." + ] + } + ], + "source": [ + "#Make Predictionn \n", + "predictions = mlp.predict(X[:100])\n", + "testing_y_pred = pd.DataFrame(predictions)\n", + "test" + ] + }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "testing_y_real = pd.DataFrame(y)\n", + "testing_y_real" ] }, { @@ -108,7 +857,18 @@ "metadata": {}, "outputs": [], "source": [ - "# your code here" + "x_test = tf.keras.utils.normalize(x_test, axis=1)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "tf.keras.optimizers.Adam(\n", + " learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-07, amsgrad=False,\n", + " name='Adam')" ] }, { @@ -144,9 +904,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.8.3" } }, "nbformat": 4, - "nbformat_minor": 2 + "nbformat_minor": 4 }