added notes and pointers to spacy model training and the Marathi example

Author: dcavar

.idea/misc.xml

@@ -65,6 +65,8 @@
 
 - [spaCy Tutorial](https://github.com/dcavar/python-tutorial-notebooks/blob/master/notebooks/spaCy%20Tutorial.ipynb)
 - [spaCy 3.x Tutorial: Transformers Spanish](https://github.com/dcavar/python-tutorial-notebooks/blob/master/notebooks/spaCy%203.x%20Tutorial%20Transformers%20Spanish.ipynb)
+- [spaCy Model from CoNLL Data](https://github.com/dcavar/python-tutorial-notebooks/blob/master/notebooks/spaCy_CoNLL_Training.ipynb)
+- [Train spaCy Model for Marathi (mr)](https://github.com/dcavar/python-tutorial-notebooks/blob/master/notebooks/Marathi/train_model.ipynb)
 - [Linear Algebra and Embeddings - spaCy](https://github.com/dcavar/python-tutorial-notebooks/blob/master/notebooks/Embeddings_and_Vectors.ipynb)
 
 

.idea/python-tutorial-notebooks.iml

@@ -81,12 +81,16 @@
  },
  {
  "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [],
+ "metadata": {
+ "jupyter": {
+ "is_executing": true
+ }
+ },
  "source": [
  "from nltk.ccg import chart, lexicon"
- ]
+ ],
+ "outputs": [],
+ "execution_count": null
  },
  {
  "cell_type": "markdown",

README.md

@@ -39,7 +39,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 5,
+ "execution_count": 2,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -57,7 +57,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 6,
+ "execution_count": 3,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -85,23 +85,23 @@
  },
  {
  "cell_type": "code",
- "execution_count": 37,
+ "execution_count": 4,
  "metadata": {},
  "outputs": [
  {
  "name": "stdout",
  "output_type": "stream",
  "text": [
- "W [[0.57916493 0.1989773 0.71685006]\n",
- " [0.06420334 0.23917944 0.03679699]]\n",
- "U [[0.44530666 0.60784364]\n",
- " [0.77164787 0.40612112]\n",
- " [0.83222563 0.69558143]]\n",
- "bias_W [[0.90328775 0.89391968 0.63126251]]\n",
- "bias_U [[0.93231218 0.7755912 ]]\n",
- "O [[0.6369282 ]\n",
- " [0.36734706]]\n",
- "bias_O [[0.93714153]]\n"
+ "W [[0.72620524 0.25526523 0.69675275]\n",
+ " [0.2365146 0.02996081 0.50613528]]\n",
+ "U [[0.63461337 0.06771906]\n",
+ " [0.86606937 0.3349142 ]\n",
+ " [0.91925414 0.75621645]]\n",
+ "bias_W [[0.71746436 0.42482447 0.26262425]]\n",
+ "bias_U [[0.68904939 0.59691488]]\n",
+ "O [[0.04374218]\n",
+ " [0.10052295]]\n",
+ "bias_O [[0.52142174]]\n"
  ]
  }
  ],
@@ -122,7 +122,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 16,
+ "execution_count": 5,
  "metadata": {},
  "outputs": [
  {
@@ -157,28 +157,28 @@
  },
  {
  "cell_type": "code",
- "execution_count": 17,
+ "execution_count": 7,
  "metadata": {},
  "outputs": [
  {
  "data": {
  "text/plain": [
- "array([1, 0])"
+ "array([3, 3])"
  ]
  },
- "execution_count": 17,
+ "execution_count": 7,
  "metadata": {},
  "output_type": "execute_result"
  }
  ],
  "source": [
- "one_hot = np.array([0, 1, 0, 0, 0, 0, 0, 0])\n",
+ "one_hot = np.array([0, 0, 0, 0, 0, 0, 0, 1])\n",
  "one_hot.dot(input_data)"
  ]
  },
  {
  "cell_type": "code",
- "execution_count": 18,
+ "execution_count": 8,
  "metadata": {},
  "outputs": [
  {
@@ -203,7 +203,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 38,
+ "execution_count": 9,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -213,7 +213,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 42,
+ "execution_count": 10,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -223,7 +223,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": null,
+ "execution_count": 11,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -232,21 +232,21 @@
  },
  {
  "cell_type": "code",
- "execution_count": 50,
+ "execution_count": 12,
  "metadata": {},
  "outputs": [
  {
  "name": "stdout",
  "output_type": "stream",
  "text": [
- "output 0.9658545034605426 - true score: 1 - loss -0.03474207364924937\n",
- "output 0.986959889282255 - true score: 0 - loss -4.3397252318950565\n",
- "output 0.9894527613414252 - true score: 0 - loss -4.5518911918432865\n",
- "output 0.995086368253607 - true score: 0 - loss -5.315741947375225\n",
- "output 0.9985133193959704 - true score: 1 - loss -0.0014877868101581678\n",
- "output 0.9988002123932317 - true score: 1 - loss -0.0012005079281317262\n",
- "output 0.9974135571146144 - true score: 1 - loss -0.002589793507494032\n",
- "output 0.9990317957413032 - true score: 0 - loss -6.940067481896969\n"
+ "output 0.6675859293553982 - true score: 1 - loss -0.4040871638764277\n",
+ "output 0.6945833449779889 - true score: 0 - loss -1.1860783525764986\n",
+ "output 0.7090513591078905 - true score: 0 - loss -1.2346085191668439\n",
+ "output 0.7203067606618183 - true score: 0 - loss -1.2740618501847558\n",
+ "output 0.7575838283922055 - true score: 1 - loss -0.2776210831773161\n",
+ "output 0.7700554259317871 - true score: 1 - loss -0.2612927849953743\n",
+ "output 0.760135340291323 - true score: 1 - loss -0.27425878222531397\n",
+ "output 0.782069969876003 - true score: 0 - loss -1.523581230446569\n"
  ]
  }
  ],
@@ -360,7 +360,7 @@
  "name": "python",
  "nbconvert_exporter": "python",
  "pygments_lexer": "ipython3",
- "version": "3.12.7"
+ "version": "3.12.3"
  }
  },
  "nbformat": 4,

notebooks/BERT_vectors.ipynb

@@ -206,7 +206,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 14,
+ "execution_count": 4,
  "metadata": {
  "scrolled": true
  },
@@ -265,7 +265,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 15,
+ "execution_count": 7,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -274,7 +274,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 16,
+ "execution_count": 8,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -306,7 +306,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 17,
+ "execution_count": 9,
  "metadata": {},
  "outputs": [
  {
@@ -330,7 +330,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 18,
+ "execution_count": 10,
  "metadata": {},
  "outputs": [],
  "source": [
@@ -353,7 +353,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 19,
+ "execution_count": 11,
  "metadata": {},
  "outputs": [
  {
@@ -377,7 +377,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 20,
+ "execution_count": 12,
  "metadata": {},
  "outputs": [
  {