diff --git a/02_activities/assignments/assignment_1.ipynb b/02_activities/assignments/assignment_1.ipynb index 28d4df017..9c9a47e3d 100644 --- a/02_activities/assignments/assignment_1.ipynb +++ b/02_activities/assignments/assignment_1.ipynb @@ -34,7 +34,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "4a3485d6-ba58-4660-a983-5680821c5719", "metadata": {}, "outputs": [], @@ -56,10 +56,288 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "id": "a431d282-f9ca-4d5d-8912-71ffc9d8ea19", "metadata": {}, - "outputs": [], + "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", + " \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", + " \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", + "
alcoholmalic_acidashalcalinity_of_ashmagnesiumtotal_phenolsflavanoidsnonflavanoid_phenolsproanthocyaninscolor_intensityhueod280/od315_of_diluted_winesprolineclass
014.231.712.4315.6127.02.803.060.282.295.641.043.921065.00
113.201.782.1411.2100.02.652.760.261.284.381.053.401050.00
213.162.362.6718.6101.02.803.240.302.815.681.033.171185.00
314.371.952.5016.8113.03.853.490.242.187.800.863.451480.00
413.242.592.8721.0118.02.802.690.391.824.321.042.93735.00
.............................................
17313.715.652.4520.595.01.680.610.521.067.700.641.74740.02
17413.403.912.4823.0102.01.800.750.431.417.300.701.56750.02
17513.274.282.2620.0120.01.590.690.431.3510.200.591.56835.02
17613.172.592.3720.0120.01.650.680.531.469.300.601.62840.02
17714.134.102.7424.596.02.050.760.561.359.200.611.60560.02
\n", + "

178 rows × 14 columns

\n", + "
" + ], + "text/plain": [ + " alcohol malic_acid ash alcalinity_of_ash magnesium total_phenols \\\n", + "0 14.23 1.71 2.43 15.6 127.0 2.80 \n", + "1 13.20 1.78 2.14 11.2 100.0 2.65 \n", + "2 13.16 2.36 2.67 18.6 101.0 2.80 \n", + "3 14.37 1.95 2.50 16.8 113.0 3.85 \n", + "4 13.24 2.59 2.87 21.0 118.0 2.80 \n", + ".. ... ... ... ... ... ... \n", + "173 13.71 5.65 2.45 20.5 95.0 1.68 \n", + "174 13.40 3.91 2.48 23.0 102.0 1.80 \n", + "175 13.27 4.28 2.26 20.0 120.0 1.59 \n", + "176 13.17 2.59 2.37 20.0 120.0 1.65 \n", + "177 14.13 4.10 2.74 24.5 96.0 2.05 \n", + "\n", + " flavanoids nonflavanoid_phenols proanthocyanins color_intensity hue \\\n", + "0 3.06 0.28 2.29 5.64 1.04 \n", + "1 2.76 0.26 1.28 4.38 1.05 \n", + "2 3.24 0.30 2.81 5.68 1.03 \n", + "3 3.49 0.24 2.18 7.80 0.86 \n", + "4 2.69 0.39 1.82 4.32 1.04 \n", + ".. ... ... ... ... ... \n", + "173 0.61 0.52 1.06 7.70 0.64 \n", + "174 0.75 0.43 1.41 7.30 0.70 \n", + "175 0.69 0.43 1.35 10.20 0.59 \n", + "176 0.68 0.53 1.46 9.30 0.60 \n", + "177 0.76 0.56 1.35 9.20 0.61 \n", + "\n", + " od280/od315_of_diluted_wines proline class \n", + "0 3.92 1065.0 0 \n", + "1 3.40 1050.0 0 \n", + "2 3.17 1185.0 0 \n", + "3 3.45 1480.0 0 \n", + "4 2.93 735.0 0 \n", + ".. ... ... ... \n", + "173 1.74 740.0 2 \n", + "174 1.56 750.0 2 \n", + "175 1.56 835.0 2 \n", + "176 1.62 840.0 2 \n", + "177 1.60 560.0 2 \n", + "\n", + "[178 rows x 14 columns]" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "from sklearn.datasets import load_wine\n", "\n", @@ -91,12 +369,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "56916892", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "178\n" + ] + } + ], "source": [ - "# Your answer here" + "# Your answer here\n", + "print(wine_df.shape[0])" ] }, { @@ -109,12 +396,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "df0ef103", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "14\n" + ] + } + ], "source": [ - "# Your answer here" + "# Your answer here\n", + "print(wine_df.shape[1])" ] }, { @@ -127,12 +423,26 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "47989426", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "int64\n", + "[0 1 2]\n", + "The variable `class` in the wine dataset is categorical with 3 classes: [0 1 2]\n" + ] + } + ], "source": [ - "# Your answer here" + "# Your answer here\n", + "print(wine_df['class'].dtypes)\n", + "#FIX: add that y variable is categorical and its possible values\n", + "print(wine_df['class'].unique())\n", + "print('The variable `class` in the wine dataset is categorical with 3 classes:', wine_df['class'].unique())" ] }, { @@ -146,12 +456,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "bd7b0910", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "13\n" + ] + } + ], "source": [ - "# Your answer here" + "# Your answer here\n", + "print(wine_df.columns[:-1].shape[0])" ] }, { @@ -175,10 +494,37 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "id": "cc899b59", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " alcohol malic_acid ash alcalinity_of_ash magnesium \\\n", + "0 1.518613 -0.562250 0.232053 -1.169593 1.913905 \n", + "1 0.246290 -0.499413 -0.827996 -2.490847 0.018145 \n", + "2 0.196879 0.021231 1.109334 -0.268738 0.088358 \n", + "3 1.691550 -0.346811 0.487926 -0.809251 0.930918 \n", + "4 0.295700 0.227694 1.840403 0.451946 1.281985 \n", + "\n", + " total_phenols flavanoids nonflavanoid_phenols proanthocyanins \\\n", + "0 0.808997 1.034819 -0.659563 1.224884 \n", + "1 0.568648 0.733629 -0.820719 -0.544721 \n", + "2 0.808997 1.215533 -0.498407 2.135968 \n", + "3 2.491446 1.466525 -0.981875 1.032155 \n", + "4 0.808997 0.663351 0.226796 0.401404 \n", + "\n", + " color_intensity hue od280/od315_of_diluted_wines proline \n", + "0 0.251717 0.362177 1.847920 1.013009 \n", + "1 -0.293321 0.406051 1.113449 0.965242 \n", + "2 0.269020 0.318304 0.788587 1.395148 \n", + "3 1.186068 -0.427544 1.184071 2.334574 \n", + "4 -0.319276 0.362177 0.449601 -0.037874 \n" + ] + } + ], "source": [ "# Select predictors (excluding the last column)\n", "predictors = wine_df.iloc[:, :-1]\n", @@ -204,7 +550,7 @@ "id": "403ef0bb", "metadata": {}, "source": [ - "> Your answer here..." + "> The variables are naturally measured in different scales. E.g. alcohol and hue are not comparable measurements. When we standardize, we put them on the same scale. Without standardization some variable(s) can dominate the classification without actually having more predictive power." ] }, { @@ -220,7 +566,7 @@ "id": "fdee5a15", "metadata": {}, "source": [ - "> Your answer here..." + "> Our response variable (LHS of an equation) doesn't need to be on the same scale as our predictors (RHS of an equation). Also, we are interested in predicting an interpretable value for 'class' not transformation of it." ] }, { @@ -236,7 +582,7 @@ "id": "f0676c21", "metadata": {}, "source": [ - "> Your answer here..." + "> This ensures reproducability anytime you have some randomness in your analysis. In this case, the split in the data (training/test) is selected randomly. A different data split would give different results (Though hopefully not so different as to change your conclusions! Then you'd have to revisit your whole analysis.). It's essential to be able to obtain the same result at each run. Suppose we're making some changes to the code to improve performance. Without a set seed, we will not know if our results are changing because of changes in our code or changes in the random draws." ] }, { @@ -251,7 +597,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "72c101f2", "metadata": {}, "outputs": [], @@ -261,7 +607,8 @@ "\n", "# split the data into a training and testing set. hint: use train_test_split !\n", "\n", - "# Your code here ..." + "## FIX: I was not using the standardized predictors, but the raw values from wine_df (!) \n", + "X_train, X_test, y_train, y_test = train_test_split(predictors_standardized, wine_df.iloc[:,-1], test_size=0.25)\n" ] }, { @@ -287,9 +634,33 @@ "execution_count": null, "id": "08818c64", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Best k: 15\n" + ] + } + ], "source": [ - "# Your code here..." + "#step 1\n", + "knn = KNeighborsClassifier()\n", + "\n", + "#step 2 \n", + "param_grid = {'n_neighbors': np.arange(1, 51)}\n", + "\n", + "# step 3 \n", + "grid_search = GridSearchCV( estimator=knn, param_grid=param_grid,cv=10, n_jobs=-1)\n", + "\n", + "#step 4\n", + "grid_search.fit(X_train, y_train)\n", + "best_k = grid_search.best_params_['n_neighbors']\n", + "best_model = grid_search.best_estimator_\n", + "\n", + "print(\"Best k:\", best_k)\n", + "\n", + "#ANOTHER CHANGE: Removed cell that manually does the grid search, since k value is now not =1" ] }, { @@ -306,11 +677,35 @@ { "cell_type": "code", "execution_count": null, - "id": "ffefa9f2", + "id": "d59c07e0", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Best k: 15\n", + "Accuracy at best k: 0.9333333333333333\n" + ] + } + ], "source": [ - "# Your code here..." + "#Create the KNN model with the best k\n", + "\n", + "\n", + "best_knn = KNeighborsClassifier(n_neighbors=best_k)\n", + "#fit the model on the training data\n", + "best_knn.fit(X_train, y_train)\n", + "\n", + "#make prediction for class\n", + "y_pred = best_knn.predict(X_test)\n", + "\n", + "#check accuracy\n", + "test_accuracy = accuracy_score(y_test, y_pred)\n", + "print(\"Best k:\", best_k)\n", + "print(\"Accuracy at best k:\", test_accuracy)\n", + "\n", + "\n" ] }, { @@ -365,7 +760,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3.10.4", + "display_name": "jmp_model_env", "language": "python", "name": "python3" }, @@ -379,12 +774,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.19" - }, - "vscode": { - "interpreter": { - "hash": "497a84dc8fec8cf8d24e7e87b6d954c9a18a327edc66feb9b9ea7e9e72cc5c7e" - } + "version": "3.10.17" } }, "nbformat": 4,