From 1b6201bf516407945ddea7009e428aeeb6facb90 Mon Sep 17 00:00:00 2001
From: Chlorophytums <118323027+Chlorophytums@users.noreply.github.com>
Date: Sun, 17 Nov 2024 20:17:48 +0700
Subject: [PATCH] Update C1_W1_Assignment.html

---
 .../W1/assignment/C1_W1_Assignment.html       | 35 ++++++++++++++-----
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/C1_Browser-based-TF-JS/W1/assignment/C1_W1_Assignment.html b/C1_Browser-based-TF-JS/W1/assignment/C1_W1_Assignment.html
index 023c6143..90f54911 100755
--- a/C1_Browser-based-TF-JS/W1/assignment/C1_W1_Assignment.html
+++ b/C1_Browser-based-TF-JS/W1/assignment/C1_W1_Assignment.html
@@ -12,7 +12,10 @@
             // can predict from the data whether the diagnosis is malignant or benign.
             const trainingData = tf.data.csv(trainingUrl, {
                 
-                // YOUR CODE HERE
+                columnNames: ['feature1', 'feature2', ..., 'featureN', 'diagnosis'],
+                columnConfigs: {
+                    diagnosis: {isLabel: true} 
+                }    // YOUR CODE HERE
                 
             });
             
@@ -21,7 +24,10 @@
             // Therefore, there is no need to convert string labels into
             // a one-hot encoded array of label values like we did in the
             // Iris dataset example. 
-            const convertedTrainingData = // YOUR CODE HERE
+            const convertedTrainingData = trainingData.map(({xs, ys}) => {
+                const labels = ys.diagnosis === 'M' ? 1 : 0; 
+                return { xs: Object.values(xs), ys: labels };
+            }).batch(32);    // YOUR CODE HERE
                   
             const testingUrl = '/data/wdbc-test.csv';
             
@@ -30,8 +36,10 @@
             // HINT: Remember that you are trying to build a classifier that 
             // can predict from the data whether the diagnosis is malignant or benign.
             const testingData = tf.data.csv(testingUrl, {
-                
-                // YOUR CODE HERE
+                columnNames: ['feature1', 'feature2', ..., 'featureN', 'diagnosis'],
+                columnConfigs: {
+                    diagnosis: {isLabel: true} 
+                } // YOUR CODE HERE
                 
             });
             
@@ -40,13 +48,16 @@
             // Therefore, there is no need to convert string labels into
             // a one-hot encoded array of label values like we did in the
             // Iris dataset example. 
-            const convertedTestingData = // YOUR CODE HERE
+            const convertedTestingData = const convertedTestingData = testingData.map(({xs, ys}) => {
+                const labels = ys.diagnosis === 'M' ? 1 : 0; 
+                return { xs: Object.values(xs), ys: labels };
+            }).batch(32);    // YOUR CODE HERE
                   
 
             // Specify the number of features in the space below.
             // HINT: You can get the number of features from the number of columns
             // and the number of labels in the training data. 
-            const numOfFeatures = // YOUR CODE HERE
+            const numOfFeatures = Object.keys(convertedTrainingData).length - 1;    // YOUR CODE HERE
             
                 
             // In the space below create a neural network that predicts 1 if the diagnosis is malignant
@@ -59,13 +70,19 @@
             // hidden layers should be enough to get a high accuracy.  
             const model = tf.sequential();
             
-            // YOUR CODE HERE
+            model.add(tf.layers.dense({units: 64, activation: 'relu', inputShape: [numOfFeatures]}));
+            model.add(tf.layers.dense({units: 32, activation: 'relu'}));
+            model.add(tf.layers.dense({units: 1, activation: 'sigmoid'}));    // YOUR CODE HERE
 
             
             
             // Compile the model using the binaryCrossentropy loss, 
             // the rmsprop optimizer, and accuracy for your metrics. 
-            model.compile(// YOUR CODE HERE);
+           model.compile({
+                optimizer: 'rmsprop',
+                loss: 'binaryCrossentropy',
+                metrics: ['accuracy']
+            });       // YOUR CODE HERE
             
             
             await model.fitDataset(convertedTrainingData, 
@@ -82,4 +99,4 @@
     </script>
 <body>
 </body>
-</html>
\ No newline at end of file
+</html>