Skip to content
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

Fix DeprecationWarning for n_iter parameter #7

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix DeprecationWarning for n_iter parameter #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
88 changes: 28 additions & 60 deletions Text+Classification+using+python,+scikit+and+nltk.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,7 @@
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": [
"#Loading the data set - training data.\n",
Expand All @@ -15,10 +13,8 @@
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
Expand All @@ -45,7 +41,7 @@
" 'talk.religion.misc']"
]
},
"execution_count": 4,
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -57,10 +53,8 @@
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand All @@ -78,18 +72,16 @@
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(11314, 130107)"
]
},
"execution_count": 6,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -104,18 +96,16 @@
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(11314, 130107)"
]
},
"execution_count": 7,
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -130,10 +120,8 @@
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
},
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# Machine Learning\n",
Expand All @@ -144,10 +132,8 @@
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
},
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"# Building a pipeline: We can write less code and do all of the above, by building a pipeline as follows:\n",
Expand All @@ -162,18 +148,16 @@
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.7738980350504514"
]
},
"execution_count": 15,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -188,26 +172,16 @@
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
},
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\javedsha\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\sklearn\\linear_model\\stochastic_gradient.py:73: DeprecationWarning: n_iter parameter is deprecated in 0.19 and will be removed in 0.21. Use max_iter and tol instead.\n",
" DeprecationWarning)\n"
]
},
{
"data": {
"text/plain": [
"0.82381837493361654"
"0.8238183749336165"
]
},
"execution_count": 16,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -217,7 +191,7 @@
"\n",
"from sklearn.linear_model import SGDClassifier\n",
"text_clf_svm = Pipeline([('vect', CountVectorizer()), ('tfidf', TfidfTransformer()),\n",
" ('clf-svm', SGDClassifier(loss='hinge', penalty='l2',alpha=1e-3, n_iter=5, random_state=42))])\n",
" ('clf-svm', SGDClassifier(loss='hinge', penalty='l2',alpha=1e-3, max_iter=5, tol=0.21, random_state=42))])\n",
"\n",
"text_clf_svm = text_clf_svm.fit(twenty_train.data, twenty_train.target)\n",
"predicted_svm = text_clf_svm.predict(twenty_test.data)\n",
Expand Down Expand Up @@ -259,9 +233,7 @@
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"data": {
Expand All @@ -287,9 +259,7 @@
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"data": {
Expand Down Expand Up @@ -333,9 +303,7 @@
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -407,7 +375,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.13"
"version": "2.7.16"
}
},
"nbformat": 4,
Expand Down
2 changes: 1 addition & 1 deletion Text+Classification+using+python,+scikit+and+nltk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@

from sklearn.linear_model import SGDClassifier
text_clf_svm = Pipeline([('vect', CountVectorizer()), ('tfidf', TfidfTransformer()),
('clf-svm', SGDClassifier(loss='hinge', penalty='l2',alpha=1e-3, n_iter=5, random_state=42))])
('clf-svm', SGDClassifier(loss='hinge', penalty='l2',alpha=1e-3, max_iter=5, tol=0.21, random_state=42))])

text_clf_svm = text_clf_svm.fit(twenty_train.data, twenty_train.target)
predicted_svm = text_clf_svm.predict(twenty_test.data)
Expand Down