fix(nlp) names gender updates

Author: stared

rnns/Names gender 1.ipynb

@@ -10,7 +10,7 @@
     "\n",
     "**Work in progress**\n",
     "\n",
-    "## Extra: Text one-hot encoding, names part 1\n",
+    "## RNN: Text one-hot encoding, names part 1\n",
     "\n",
     "We use [US Baby Names - Kaggle Dataset](https://www.kaggle.com/kaggle/us-baby-names).\n",
     "If needed, you can use: `!wget https://www.dropbox.com/s/s14l44ptqevgech/NationalNames.csv.zip?dl=1`\n",
@@ -49,7 +49,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "names = pd.read_csv(\"NationalNames.csv\")"
+    "names = pd.read_csv(\"./data/NationalNames.csv\")"
    ]
   },
   {
@@ -283,7 +283,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with h5py.File(\"names.h5\") as f:\n",
+    "with h5py.File(\"data/names_dense.h5\") as f:\n",
     "    f.create_dataset('X_train', data=X_train)\n",
     "    f.create_dataset('y_train', data=y_train)\n",
     "    f.create_dataset('X_test', data=X_test)\n",
@@ -302,9 +302,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python [default]",
+   "display_name": "Python [conda env:py37]",
    "language": "python",
-   "name": "python3"
+   "name": "conda-env-py37-py"
   },
   "language_info": {
    "codemirror_mode": {
@@ -316,7 +316,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.4"
+   "version": "3.7.2"
   },
   "varInspector": {
    "cols": {

rnns/Names gender 2.ipynb

@@ -10,7 +10,7 @@
     "\n",
     "**Work in progress**\n",
     "\n",
-    "## Extra: LSTMs for on-hot encoded data\n",
+    "## RNNs: LSTMs for on-hot encoded data\n",
     "\n",
     "We use recurrent networks. For wonderful introductions:\n",
     "\n",
@@ -29,6 +29,15 @@
     "* [Contiguous() and permute()](https://discuss.pytorch.org/t/contiguous-and-permute/20673)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install livelossplot --quiet"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -54,7 +63,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with h5py.File(\"../data/preprocessed/names.h5\", 'r') as data:\n",
+    "with h5py.File(\"./data/names_dense.h5\", 'r') as data:\n",
     "    X_train = data['X_train'].value\n",
     "    y_train = data['y_train'].value\n",
     "    X_test = data['X_test'].value\n",
@@ -79,9 +88,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(X_train.shape)  # should be: (24783, 26, 15)\n",
+    "print(X_train.shape)  # should be: (24783, 26, 16)\n",
     "print(y_train.shape)  # should be: (24783)\n",
-    "print(X_test.shape)   # should be: (8261, 26, 15)\n",
+    "print(X_test.shape)   # should be: (8261, 26, 16)\n",
     "print(y_test.shape)   # should be: (8261)"
    ]
   },

rnns/Word vectors.ipynb

@@ -465,6 +465,18 @@
    "language": "python",
    "name": "conda-env-py37-py"
   },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.2"
+  },
   "varInspector": {
    "cols": {
     "lenName": 16,