Merge pull request #5105 from MaxGhenis/patch-1

Nits in basic_regression.ipynb

samples/core/tutorials/keras/basic_regression.ipynb

@@ -185,7 +185,7 @@
       },
       "cell_type": "markdown",
       "source": [
-        "### Examples and features \n",
+        "### Examples and features\n",
         "\n",
         "This dataset is much smaller than the others we've worked with so far: it has 506 total examples are split between 404 training examples and 102 test examples:"
       ]
@@ -319,7 +319,7 @@
       },
       "cell_type": "code",
       "source": [
-        "# Test data is *not* used when calculating the mean and std.\n",
+        "# Test data is *not* used when calculating the mean and std\n",
         "\n",
         "mean = train_data.mean(axis=0)\n",
         "std = train_data.std(axis=0)\n",
@@ -338,7 +338,7 @@
       },
       "cell_type": "markdown",
       "source": [
-        "Although the model *might* converge without feature normalization, it makes training more difficult, and it makes the resulting model more dependant on the choice of units used in the input."
+        "Although the model *might* converge without feature normalization, it makes training more difficult, and it makes the resulting model more dependent on the choice of units used in the input."
       ]
     },
     {
@@ -363,7 +363,7 @@
       "source": [
         "def build_model():\n",
         "  model = keras.Sequential([\n",
-        "    keras.layers.Dense(64, activation=tf.nn.relu, \n",
+        "    keras.layers.Dense(64, activation=tf.nn.relu,\n",
         "                       input_shape=(train_data.shape[1],)),\n",
         "    keras.layers.Dense(64, activation=tf.nn.relu),\n",
         "    keras.layers.Dense(1)\n",
@@ -402,9 +402,9 @@
       },
       "cell_type": "code",
       "source": [
-        "# Display training progress by printing a single dot for each completed epoch.\n",
+        "# Display training progress by printing a single dot for each completed epoch\n",
         "class PrintDot(keras.callbacks.Callback):\n",
-        "  def on_epoch_end(self,epoch,logs):\n",
+        "  def on_epoch_end(self, epoch, logs):\n",
         "    if epoch % 100 == 0: print('')\n",
         "    print('.', end='')\n",
         "\n",
@@ -443,12 +443,12 @@
         "  plt.figure()\n",
         "  plt.xlabel('Epoch')\n",
         "  plt.ylabel('Mean Abs Error [1000$]')\n",
-        "  plt.plot(history.epoch, np.array(history.history['mean_absolute_error']), \n",
+        "  plt.plot(history.epoch, np.array(history.history['mean_absolute_error']),\n",
         "           label='Train Loss')\n",
         "  plt.plot(history.epoch, np.array(history.history['val_mean_absolute_error']),\n",
         "           label = 'Val loss')\n",
         "  plt.legend()\n",
-        "  plt.ylim([0,5])\n",
+        "  plt.ylim([0, 5])\n",
         "\n",
         "plot_history(history)"
       ],
@@ -477,7 +477,7 @@
       "source": [
         "model = build_model()\n",
         "\n",
-        "# The patience parameter is the amount of epochs to check for improvement.\n",
+        "# The patience parameter is the amount of epochs to check for improvement\n",
         "early_stop = keras.callbacks.EarlyStopping(monitor='val_loss', patience=20)\n",
         "\n",
         "history = model.fit(train_data, train_labels, epochs=EPOCHS,\n",
@@ -544,7 +544,7 @@
         "plt.axis('equal')\n",
         "plt.xlim(plt.xlim())\n",
         "plt.ylim(plt.ylim())\n",
-        "_ = plt.plot([-100, 100],[-100,100])\n"
+        "_ = plt.plot([-100, 100], [-100, 100])\n"
       ],
       "execution_count": 0,
       "outputs": []