Skip to content

Modifications for Windows support in Chapters 4, 5, 6, 10 and 11 #66

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 16 commits into from
Jun 21, 2021
Merged

Modifications for Windows support in Chapters 4, 5, 6, 10 and 11 #66

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
30a539d
[Ch6Nb02] Fixed errors and compatibility issues
jatinpapreja Jun 13, 2021
782afc2
[Ch6Nb05] Fixed compatibility issues
jatinpapreja Jun 13, 2021
47a93a9
[Ch4Nb05] Fixed a minor error
jatinpapreja Jun 13, 2021
2ef376a
[Ch6Nb04] Added commands to download and unzip 'glove.6B.zip'
KUMAR-APURVA Jun 13, 2021
d2ebc54
[Ch6Nb03] Added missing functions and missing files.
KUMAR-APURVA Jun 13, 2021
e8422ff
These files were missing in [Ch6Nb03]
KUMAR-APURVA Jun 13, 2021
b03dfa7
Merge branch 'practical-nlp:master' into master
jatinpapreja Jun 13, 2021
12d58a1
[Ch5Nb02] Fixed path and compatibility issues
jatinpapreja Jun 19, 2021
6bbf38a
[Ch5Nb01] Fixed version and path issues.
KUMAR-APURVA Jun 19, 2021
7d15317
[Ch5Nb04] Added alternatives of linux commands
jatinpapreja Jun 19, 2021
1dda22b
[Fix] Renamed notebook to correct filename
kartikay-bagla Jun 20, 2021
ee23d37
[Ch5Nb05] Fixed windows compatibility
KUMAR-APURVA Jun 20, 2021
501b24e
[Ch10Nb03] Added compatibilities for windows user
KUMAR-APURVA Jun 20, 2021
e447951
[Ch10Nb01] Added compatibilities for windows user
jatinpapreja Jun 20, 2021
de656c6
[Ch11Nb01] Fixed keras-tuner version
KUMAR-APURVA Jun 20, 2021
77d21b9
[Ch10Nb02] Fixed path issues for windows user
jatinpapreja Jun 20, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3,811 changes: 1,914 additions & 1,897 deletions Ch10/01_BioBERT_Demo.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

564 changes: 126 additions & 438 deletions Ch10/02_LexNLP.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

3,031 changes: 1,545 additions & 1,486 deletions Ch10/03_FinBERT.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

648 changes: 318 additions & 330 deletions Ch11/01_AutoML_Demo.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions Ch4/05_DeepNN_Example.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@
"except ModuleNotFoundError:\n",
" \n",
" if not os.path.exists(os.getcwd()+'\\\\Data\\\\glove.6B'):\n",
" os.makdir(os.getcwd()+'\\\\Data\\\\glove.6B')\n",
" os.mkdir(os.getcwd()+'\\\\Data\\\\glove.6B')\n",
" \n",
" url='http://nlp.stanford.edu/data/glove.6B.zip' \n",
" path=os.getcwd()+'\\Data' \n",
Expand Down Expand Up @@ -549,7 +549,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.0"
"version": "3.7.4"
}
},
"nbformat": 4,
Expand Down
396 changes: 291 additions & 105 deletions Ch5/01_KPE.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

91 changes: 46 additions & 45 deletions Ch5/02_NERTraining.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 1,
"metadata": {
"colab": {},
"colab_type": "code",
Expand All @@ -37,7 +37,9 @@
"from pprint import pprint\n",
"from sklearn.metrics import f1_score,classification_report\n",
"from sklearn.pipeline import Pipeline\n",
"import string\n"
"import string\n",
"import warnings\n",
"warnings.filterwarnings('ignore')"
]
},
{
Expand All @@ -52,7 +54,7 @@
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 2,
"metadata": {
"colab": {},
"colab_type": "code",
Expand All @@ -79,12 +81,12 @@
" words.append(word)\n",
" tags.append(tag)\n",
" fh.close()\n",
" return myoutput\n"
" return myoutput"
]
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 3,
"metadata": {
"colab": {},
"colab_type": "code",
Expand Down Expand Up @@ -150,7 +152,7 @@
" wordfeats[\"nextNextTag\"] = sen_tags[i + 2][1]\n",
" #That is it! You can add whatever you want!\n",
" feats.append(wordfeats)\n",
" return feats\n"
" return feats"
]
},
{
Expand All @@ -165,7 +167,7 @@
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 4,
"metadata": {
"colab": {},
"colab_type": "code",
Expand Down Expand Up @@ -195,7 +197,7 @@
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 5,
"metadata": {
"colab": {},
"colab_type": "code",
Expand All @@ -217,7 +219,7 @@
" print(metrics.flat_f1_score(Y_dev, y_pred,average='weighted', labels=labels))\n",
" print(metrics.flat_classification_report(Y_dev, y_pred, labels=sorted_labels, digits=3))\n",
" #print(metrics.sequence_accuracy_score(Y_dev, y_pred))\n",
" get_confusion_matrix(Y_dev, y_pred,labels=sorted_labels)\n"
" get_confusion_matrix(Y_dev, y_pred,labels=sorted_labels)"
]
},
{
Expand All @@ -232,7 +234,7 @@
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 6,
"metadata": {
"colab": {},
"colab_type": "code",
Expand All @@ -258,12 +260,12 @@
" cell = \"%{0}.0f\".format(columnwidth) % cm[i, j]\n",
" sum = sum + int(cell)\n",
" print(cell, end=\" \")\n",
" print(sum) #Prints the total number of instances per cat at the end.\n"
" print(sum) #Prints the total number of instances per cat at the end."
]
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 7,
"metadata": {
"colab": {},
"colab_type": "code",
Expand All @@ -278,7 +280,7 @@
" for yseq_true, yseq_pred in zip(y_true, y_pred):\n",
" trues.extend(yseq_true)\n",
" preds.extend(yseq_pred)\n",
" print_cm(confusion_matrix(trues,preds,labels),labels)\n"
" print_cm(confusion_matrix(trues,preds,labels),labels)"
]
},
{
Expand All @@ -293,7 +295,7 @@
},
{
"cell_type": "code",
"execution_count": 0,
"execution_count": 8,
"metadata": {
"colab": {},
"colab_type": "code",
Expand All @@ -307,19 +309,21 @@
"text": [
"Training a Sequence classification model with CRF\n",
"0.9255103670420659\n",
" precision recall f1-score support\n",
" precision recall f1-score support\n",
"\n",
" O 0.973 0.981 0.977 38323\n",
" B-LOC 0.694 0.765 0.728 1668\n",
" I-LOC 0.738 0.482 0.584 257\n",
" B-MISC 0.648 0.309 0.419 702\n",
" I-MISC 0.626 0.505 0.559 216\n",
" B-ORG 0.670 0.561 0.611 1661\n",
" I-ORG 0.551 0.704 0.618 835\n",
" B-PER 0.773 0.766 0.769 1617\n",
" I-PER 0.819 0.886 0.851 1156\n",
" O 0.973 0.981 0.977 38323\n",
" B-LOC 0.694 0.765 0.728 1668\n",
" I-LOC 0.738 0.482 0.584 257\n",
" B-MISC 0.648 0.309 0.419 702\n",
" I-MISC 0.626 0.505 0.559 216\n",
" B-ORG 0.670 0.561 0.611 1661\n",
" I-ORG 0.551 0.704 0.618 835\n",
" B-PER 0.773 0.766 0.769 1617\n",
" I-PER 0.819 0.886 0.851 1156\n",
"\n",
"avg / total 0.926 0.928 0.926 46435\n",
" accuracy 0.928 46435\n",
" macro avg 0.721 0.662 0.679 46435\n",
"weighted avg 0.926 0.928 0.926 46435\n",
"\n",
"\n",
"\n",
Expand All @@ -338,10 +342,18 @@
}
],
"source": [
"\n",
"def main():\n",
" train_path = 'conlldata/train.txt'\n",
" test_path = 'conlldata/test.txt'\n",
" \n",
" try:\n",
" from google.colab import files\n",
" uploaded = files.upload()\n",
" # files are present in Data/conlldata\n",
" train_path = 'train.txt'\n",
" test_path = 'test.txt'\n",
" except:\n",
" train_path = 'Data/conlldata/train.txt'\n",
" test_path = 'Data/conlldata/test.txt'\n",
" \n",
" conll_train = load__data_conll(train_path)\n",
" conll_dev = load__data_conll(test_path)\n",
" \n",
Expand All @@ -352,7 +364,7 @@
" print(\"Done with sequence model\")\n",
"\n",
"if __name__==\"__main__\":\n",
" main()\n"
" main()"
]
},
{
Expand All @@ -364,17 +376,6 @@
"source": [
"This is pretty good. We already have a model which has an F-score of 92%!!!"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "reO-wnZocnB2"
},
"outputs": [],
"source": []
}
],
"metadata": {
Expand All @@ -383,21 +384,21 @@
"provenance": []
},
"kernelspec": {
"display_name": "Python 2",
"display_name": "Python 3",
"language": "python",
"name": "python2"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.17"
"pygments_lexer": "ipython3",
"version": "3.7.4"
}
},
"nbformat": 4,
Expand Down
Loading