Merge pull request #226 from MarkFischinger/fix/examples

Fixed Python Notebook Examples
mlpack · May 1, 2024 · 5b2062c · 5b2062c
2 parents 91a927f + 7f5f52f
commit 5b2062c
Show file tree

Hide file tree

Showing 14 changed files with 2,564 additions and 840 deletions.
diff --git a/airbnb_price_prediction_regression/airbnb_price_prediction_regression_py.ipynb b/airbnb_price_prediction_regression/airbnb_price_prediction_regression_py.ipynb
@@ -2461,7 +2461,7 @@
    "id": "bb903f9b",
    "metadata": {},
    "source": [
-    "- Mean Absoulte Error: 0.37\n",
+    "- Mean Absolute Error: 0.37\n",
     "- Mean Squared Error: 0.26\n",
     "- Root Mean Squared Error: 0.51\n",
     "- R2 score: 0.46"

diff --git a/avocado_price_prediction_with_linear_regression/avocado_price_prediction_with_lr_py.ipynb b/avocado_price_prediction_with_linear_regression/avocado_price_prediction_with_lr_py.ipynb
diff --git a/breast_cancer_wisconsin_transformation_with_pca/breast-cancer-wisconsin-pca-py.ipynb b/breast_cancer_wisconsin_transformation_with_pca/breast-cancer-wisconsin-pca-py.ipynb
diff --git a/...diction_with_linear_regression/California_housing_prices_predictions_with_lr_python.ipynb b/...diction_with_linear_regression/California_housing_prices_predictions_with_lr_python.ipynb
diff --git a/cifar10_transformation_with_pca/cifar-10-pca-py.ipynb b/cifar10_transformation_with_pca/cifar-10-pca-py.ipynb
diff --git a/contact_tracing_clustering_with_dbscan/contact_tracing_dbscan_py.ipynb b/contact_tracing_clustering_with_dbscan/contact_tracing_dbscan_py.ipynb
diff --git a/customer_personality_clustering/customer_personality_clustering_py.ipynb b/customer_personality_clustering/customer_personality_clustering_py.ipynb
diff --git a/forest_covertype_prediction_with_random_forests/covertype-rf-py.ipynb b/forest_covertype_prediction_with_random_forests/covertype-rf-py.ipynb
@@ -1,146 +1,169 @@
 {
-  "metadata":{
-    "language_info":{
-      "name":"python",
-      "version":"3.7.6",
-      "mimetype":"text/x-python",
-      "codemirror_mode":{
-        "name":"ipython",
-        "version":3
-      },
-      "pygments_lexer":"ipython3",
-      "nbconvert_exporter":"python",
-      "file_extension":".py"
-    },
-    "kernelspec":{
-      "name":"python3",
-      "display_name":"Python 3",
-      "language":"python"
-    }
-  },
-  "nbformat_minor":4,
-  "nbformat":4,
-  "cells":[
+  "cells": [
     {
-      "cell_type":"markdown",
-      "source":"[![Binder](https://mybinder.org/badge_logo.svg)](https://lab.mlpack.org/v2/gh/mlpack/examples/master?urlpath=lab%2Ftree%2Fforest_covertype_prediction_with_random_forests%2Fcovertype-rf-py.ipynb)",
-      "metadata":{
-
-      }
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "[![Binder](https://mybinder.org/badge_logo.svg)](https://lab.mlpack.org/v2/gh/mlpack/examples/master?urlpath=lab%2Ftree%2Fforest_covertype_prediction_with_random_forests%2Fcovertype-rf-py.ipynb)"
+      ]
     },
     {
-      "cell_type":"code",
-      "source":"# @file covertype-rf-py.ipynb\n#\n# Classification using Random Forest on the Covertype dataset.",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 11,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":11,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "# @file covertype-rf-py.ipynb\n",
+        "#\n",
+        "# Classification using Random Forest on the Covertype dataset."
       ]
     },
     {
-      "cell_type":"code",
-      "source":"import mlpack\nimport pandas as pd\nimport numpy as np",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":12,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "import mlpack\n",
+        "import pandas as pd\n",
+        "import numpy as np"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"# Load the dataset from an online URL.\ndf = pd.read_csv('https://lab.mlpack.org/data/covertype-small.csv.gz')",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 13,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":13,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "# Load the dataset from an online URL.\n",
+        "df = pd.read_csv('https://datasets.mlpack.org/covertype-small.csv.gz')"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"# Split the labels.\nlabels = df['label']\ndataset = df.drop('label', 1)",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":14,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "# Split the labels.\n",
+        "labels = df['label']\n",
+        "dataset = df.drop('label', axis=1)"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"# Split the dataset using mlpack. The output comes back as a dictionary, which\n# we'll unpack for clarity of code.\noutput = mlpack.preprocess_split(input=dataset, input_labels=labels, test_ratio=0.3)",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 15,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":15,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "# Split the dataset using mlpack. The output comes back as a dictionary, which\n",
+        "# we'll unpack for clarity of code.\n",
+        "output = mlpack.preprocess_split(input_=dataset, input_labels=labels, test_ratio=0.3)"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"training_set = output['training']\ntraining_labels = output['training_labels']\ntest_set = output['test']\ntest_labels = output['test_labels']",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 16,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":16,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "training_set = output['training']\n",
+        "training_labels = output['training_labels']\n",
+        "test_set = output['test']\n",
+        "test_labels = output['test_labels']"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"# Train a random forest.\noutput = mlpack.random_forest(training=training_set, labels=training_labels,\n    print_training_accuracy=True, num_trees=10, minimum_leaf_size=3)",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 17,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":17,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "# Train a random forest.\n",
+        "output = mlpack.random_forest(training=training_set, labels=training_labels,\n",
+        "    print_training_accuracy=True, num_trees=10, minimum_leaf_size=3)"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"random_forest = output['output_model']",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 18,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":18,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "random_forest = output['output_model']"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"# Predict the labels of the test points.\noutput = mlpack.random_forest(input_model=random_forest, test=test_set)",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 19,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":19,
-      "outputs":[
-
+      "outputs": [],
+      "source": [
+        "# Predict the labels of the test points.\n",
+        "output = mlpack.random_forest(input_model=random_forest, test=test_set)"
       ]
     },
     {
-      "cell_type":"code",
-      "source":"# Now print the accuracy. The 'probabilities' output could also be used to\n# generate an ROC curve.\ncorrect = np.sum(output['predictions'] == test_labels.flatten())\nprint(str(correct) + ' correct out of ' + str(len(test_labels)) +\n      ' (' + str(100 * float(correct) / float(len(test_labels))) + '%).')",
-      "metadata":{
-        "trusted":true
+      "cell_type": "code",
+      "execution_count": 20,
+      "metadata": {
+        "trusted": true
       },
-      "execution_count":20,
-      "outputs":[
+      "outputs": [
         {
-          "name":"stdout",
-          "text":"24513 correct out of 30000 (81.71%).\n",
-          "output_type":"stream"
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "24513 correct out of 30000 (81.71%).\n"
+          ]
         }
+      ],
+      "source": [
+        "# Now print the accuracy. The 'probabilities' output could also be used to\n",
+        "# generate an ROC curve.\n",
+        "correct = np.sum(output['predictions'] == test_labels.flatten())\n",
+        "print(str(correct) + ' correct out of ' + str(len(test_labels)) +\n",
+        "      ' (' + str(100 * float(correct) / float(len(test_labels))) + '%).')"
       ]
     }
-  ]
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.7.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 4
 }
diff --git a/...ion_classification_with_Adaboost/graduate-admission-classification-with-adaboost-py.ipynb b/...ion_classification_with_Adaboost/graduate-admission-classification-with-adaboost-py.ipynb
diff --git a/iris-classification/iris-classification-py.ipynb b/iris-classification/iris-classification-py.ipynb