Skip to content

M
Major Project machine
Commit 5cd7726d authored by Jonathan Poalses's avatar Jonathan Poalses
Browse files
Options

Added GNB, KNeighbour, and SVC ML implementations

parent d3ae4489
Hide whitespace changes
Inline Side-by-side
Showing with 87 additions and 87 deletions
nlp_gnb.ipynb
View file @ 5cd7726d
......@@ -2,12 +2,12 @@
"cells": [
{
"cell_type": "code",
"execution_count": 265,
"execution_count": 105,
"metadata": {
"collapsed": true,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.264368Z",
"start_time": "2023-05-18T01:49:55.259004Z"
"end_time": "2023-05-18T01:58:43.027132Z",
"start_time": "2023-05-18T01:58:43.019344Z"
}
},
"outputs": [],
......@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
"execution_count": 266,
"execution_count": 106,
"outputs": [],
"source": [
"data = vectorizer.fit_transform(edn.loads(open(\"sample_data.txt\").read()))\n",
......@@ -30,29 +30,29 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.286323Z",
"start_time": "2023-05-18T01:49:55.267563Z"
"end_time": "2023-05-18T01:58:43.043055Z",
"start_time": "2023-05-18T01:58:43.026725Z"
}
}
},
{
"cell_type": "code",
"execution_count": 267,
"execution_count": 107,
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=1999)"
"X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=42)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.292277Z",
"start_time": "2023-05-18T01:49:55.288051Z"
"end_time": "2023-05-18T01:58:43.066023Z",
"start_time": "2023-05-18T01:58:43.054110Z"
}
}
},
{
"cell_type": "code",
"execution_count": 268,
"execution_count": 108,
"outputs": [],
"source": [
"from sklearn.naive_bayes import GaussianNB"
......@@ -60,21 +60,21 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.298594Z",
"start_time": "2023-05-18T01:49:55.295927Z"
"end_time": "2023-05-18T01:58:43.066927Z",
"start_time": "2023-05-18T01:58:43.060309Z"
}
}
},
{
"cell_type": "code",
"execution_count": 269,
"execution_count": 109,
"outputs": [
{
"data": {
"text/plain": "KNeighborsClassifier()",
"text/html": "<style>#sk-container-id-25 {color: black;background-color: white;}#sk-container-id-25 pre{padding: 0;}#sk-container-id-25 div.sk-toggleable {background-color: white;}#sk-container-id-25 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-25 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-25 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-25 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-25 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-25 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-25 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-25 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-25 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-25 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-25 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-25 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-25 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-25 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-25 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-25 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-25 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-25 div.sk-item {position: relative;z-index: 1;}#sk-container-id-25 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-25 div.sk-item::before, #sk-container-id-25 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-25 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-25 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-25 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-25 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-25 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-25 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-25 div.sk-label-container {text-align: center;}#sk-container-id-25 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-25 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-25\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-25\" type=\"checkbox\" checked><label for=\"sk-estimator-id-25\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier()</pre></div></div></div></div></div>"
"text/plain": "GaussianNB()",
"text/html": "<style>#sk-container-id-14 {color: black;background-color: white;}#sk-container-id-14 pre{padding: 0;}#sk-container-id-14 div.sk-toggleable {background-color: white;}#sk-container-id-14 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-14 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-14 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-14 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-14 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-14 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-14 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-14 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-14 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-14 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-14 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-14 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-14 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-14 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-14 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-14 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-14 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-14 div.sk-item {position: relative;z-index: 1;}#sk-container-id-14 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-14 div.sk-item::before, #sk-container-id-14 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-14 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-14 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-14 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-14 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-14 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-14 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-14 div.sk-label-container {text-align: center;}#sk-container-id-14 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-14 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-14\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" checked><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
},
"execution_count": 269,
"execution_count": 109,
"metadata": {},
"output_type": "execute_result"
}
......@@ -86,14 +86,14 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.315007Z",
"start_time": "2023-05-18T01:49:55.303883Z"
"end_time": "2023-05-18T01:58:43.077601Z",
"start_time": "2023-05-18T01:58:43.067375Z"
}
}
},
{
"cell_type": "code",
"execution_count": 270,
"execution_count": 110,
"outputs": [],
"source": [
"predicted=gnb.predict((X_test).toarray())\n",
......@@ -102,20 +102,20 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.330297Z",
"start_time": "2023-05-18T01:49:55.311459Z"
"end_time": "2023-05-18T01:58:43.082487Z",
"start_time": "2023-05-18T01:58:43.078846Z"
}
}
},
{
"cell_type": "code",
"execution_count": 271,
"execution_count": 111,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"20.00%\n"
"75.00%\n"
]
}
],
......@@ -126,20 +126,20 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.357313Z",
"start_time": "2023-05-18T01:49:55.326780Z"
"end_time": "2023-05-18T01:58:43.093743Z",
"start_time": "2023-05-18T01:58:43.084280Z"
}
}
},
{
"cell_type": "code",
"execution_count": 272,
"execution_count": 112,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 20.00%\n"
" 75.00%\n"
]
}
],
......@@ -149,8 +149,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:55.362376Z",
"start_time": "2023-05-18T01:49:55.341241Z"
"end_time": "2023-05-18T01:58:43.109002Z",
"start_time": "2023-05-18T01:58:43.087892Z"
}
}
}
......
nlp_kn.ipynb
View file @ 5cd7726d
......@@ -2,12 +2,12 @@
"cells": [
{
"cell_type": "code",
"execution_count": 257,
"execution_count": 57,
"metadata": {
"collapsed": true,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.014295Z",
"start_time": "2023-05-18T01:49:38.007387Z"
"end_time": "2023-05-18T01:58:46.040817Z",
"start_time": "2023-05-18T01:58:46.036097Z"
}
},
"outputs": [],
......@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
"execution_count": 258,
"execution_count": 58,
"outputs": [],
"source": [
"data = vectorizer.fit_transform(edn.loads(open(\"sample_data.txt\").read()))\n",
......@@ -30,29 +30,29 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.035222Z",
"start_time": "2023-05-18T01:49:38.012819Z"
"end_time": "2023-05-18T01:58:46.083314Z",
"start_time": "2023-05-18T01:58:46.042782Z"
}
}
},
{
"cell_type": "code",
"execution_count": 259,
"execution_count": 59,
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=1999)"
"X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=42)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.048317Z",
"start_time": "2023-05-18T01:49:38.038940Z"
"end_time": "2023-05-18T01:58:46.099054Z",
"start_time": "2023-05-18T01:58:46.093034Z"
}
}
},
{
"cell_type": "code",
"execution_count": 260,
"execution_count": 60,
"outputs": [],
"source": [
"from sklearn.neighbors import KNeighborsClassifier"
......@@ -60,21 +60,21 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.053101Z",
"start_time": "2023-05-18T01:49:38.046545Z"
"end_time": "2023-05-18T01:58:46.103466Z",
"start_time": "2023-05-18T01:58:46.099846Z"
}
}
},
{
"cell_type": "code",
"execution_count": 261,
"execution_count": 61,
"outputs": [
{
"data": {
"text/plain": "GaussianNB()",
"text/html": "<style>#sk-container-id-24 {color: black;background-color: white;}#sk-container-id-24 pre{padding: 0;}#sk-container-id-24 div.sk-toggleable {background-color: white;}#sk-container-id-24 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-24 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-24 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-24 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-24 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-24 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-24 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-24 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-24 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-24 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-24 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-24 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-24 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-24 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-24 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-24 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-24 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-24 div.sk-item {position: relative;z-index: 1;}#sk-container-id-24 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-24 div.sk-item::before, #sk-container-id-24 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-24 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-24 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-24 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-24 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-24 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-24 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-24 div.sk-label-container {text-align: center;}#sk-container-id-24 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-24 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-24\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-24\" type=\"checkbox\" checked><label for=\"sk-estimator-id-24\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
"text/plain": "KNeighborsClassifier()",
"text/html": "<style>#sk-container-id-8 {color: black;background-color: white;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-8 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-8 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier()</pre></div></div></div></div></div>"
},
"execution_count": 261,
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
......@@ -86,14 +86,14 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.074733Z",
"start_time": "2023-05-18T01:49:38.058388Z"
"end_time": "2023-05-18T01:58:46.117344Z",
"start_time": "2023-05-18T01:58:46.110609Z"
}
}
},
{
"cell_type": "code",
"execution_count": 262,
"execution_count": 62,
"outputs": [],
"source": [
"predicted=knc.predict(X_test)\n",
......@@ -102,14 +102,14 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.086974Z",
"start_time": "2023-05-18T01:49:38.072132Z"
"end_time": "2023-05-18T01:58:46.122772Z",
"start_time": "2023-05-18T01:58:46.118837Z"
}
}
},
{
"cell_type": "code",
"execution_count": 263,
"execution_count": 63,
"outputs": [
{
"name": "stdout",
......@@ -126,14 +126,14 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.087358Z",
"start_time": "2023-05-18T01:49:38.077370Z"
"end_time": "2023-05-18T01:58:46.126935Z",
"start_time": "2023-05-18T01:58:46.124164Z"
}
}
},
{
"cell_type": "code",
"execution_count": 264,
"execution_count": 64,
"outputs": [
{
"name": "stdout",
......@@ -149,8 +149,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:49:38.090517Z",
"start_time": "2023-05-18T01:49:38.085248Z"
"end_time": "2023-05-18T01:58:46.132578Z",
"start_time": "2023-05-18T01:58:46.128149Z"
}
}
}
......
nlp_svc.ipynb
View file @ 5cd7726d
......@@ -2,12 +2,12 @@
"cells": [
{
"cell_type": "code",
"execution_count": 366,
"execution_count": 438,
"metadata": {
"collapsed": true,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.666452Z",
"start_time": "2023-05-18T01:53:55.643356Z"
"end_time": "2023-05-18T01:58:39.308492Z",
"start_time": "2023-05-18T01:58:39.302389Z"
}
},
"outputs": [],
......@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
"execution_count": 367,
"execution_count": 439,
"outputs": [],
"source": [
"data = vectorizer.fit_transform(edn.loads(open(\"sample_data.txt\").read()))\n",
......@@ -30,29 +30,29 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.696031Z",
"start_time": "2023-05-18T01:53:55.660318Z"
"end_time": "2023-05-18T01:58:39.340125Z",
"start_time": "2023-05-18T01:58:39.312108Z"
}
}
},
{
"cell_type": "code",
"execution_count": 368,
"execution_count": 440,
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=1999)"
"X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=42)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.703863Z",
"start_time": "2023-05-18T01:53:55.699895Z"
"end_time": "2023-05-18T01:58:39.351322Z",
"start_time": "2023-05-18T01:58:39.341456Z"
}
}
},
{
"cell_type": "code",
"execution_count": 369,
"execution_count": 441,
"outputs": [],
"source": [
"from sklearn.svm import SVC"
......@@ -60,21 +60,21 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.709149Z",
"start_time": "2023-05-18T01:53:55.705840Z"
"end_time": "2023-05-18T01:58:39.368348Z",
"start_time": "2023-05-18T01:58:39.355705Z"
}
}
},
{
"cell_type": "code",
"execution_count": 370,
"execution_count": 442,
"outputs": [
{
"data": {
"text/plain": "SVC()",
"text/html": "<style>#sk-container-id-37 {color: black;background-color: white;}#sk-container-id-37 pre{padding: 0;}#sk-container-id-37 div.sk-toggleable {background-color: white;}#sk-container-id-37 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-37 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-37 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-37 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-37 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-37 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-37 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-37 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-37 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-37 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-37 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-37 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-37 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-37 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-37 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-37 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-37 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-37 div.sk-item {position: relative;z-index: 1;}#sk-container-id-37 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-37 div.sk-item::before, #sk-container-id-37 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-37 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-37 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-37 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-37 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-37 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-37 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-37 div.sk-label-container {text-align: center;}#sk-container-id-37 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-37 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-37\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-37\" type=\"checkbox\" checked><label for=\"sk-estimator-id-37\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC()</pre></div></div></div></div></div>"
"text/html": "<style>#sk-container-id-46 {color: black;background-color: white;}#sk-container-id-46 pre{padding: 0;}#sk-container-id-46 div.sk-toggleable {background-color: white;}#sk-container-id-46 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-46 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-46 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-46 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-46 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-46 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-46 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-46 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-46 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-46 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-46 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-46 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-46 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-46 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-46 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-46 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-46 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-46 div.sk-item {position: relative;z-index: 1;}#sk-container-id-46 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-46 div.sk-item::before, #sk-container-id-46 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-46 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-46 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-46 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-46 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-46 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-46 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-46 div.sk-label-container {text-align: center;}#sk-container-id-46 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-46 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-46\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-46\" type=\"checkbox\" checked><label for=\"sk-estimator-id-46\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC()</pre></div></div></div></div></div>"
},
"execution_count": 370,
"execution_count": 442,
"metadata": {},
"output_type": "execute_result"
}
......@@ -86,14 +86,14 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.729099Z",
"start_time": "2023-05-18T01:53:55.719679Z"
"end_time": "2023-05-18T01:58:39.384555Z",
"start_time": "2023-05-18T01:58:39.371641Z"
}
}
},
{
"cell_type": "code",
"execution_count": 371,
"execution_count": 443,
"outputs": [],
"source": [
"predicted=svc.predict(X_test)\n",
......@@ -102,20 +102,20 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.733844Z",
"start_time": "2023-05-18T01:53:55.730968Z"
"end_time": "2023-05-18T01:58:39.393847Z",
"start_time": "2023-05-18T01:58:39.386304Z"
}
}
},
{
"cell_type": "code",
"execution_count": 372,
"execution_count": 444,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"35.00%\n"
"55.00%\n"
]
}
],
......@@ -126,20 +126,20 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.738217Z",
"start_time": "2023-05-18T01:53:55.735115Z"
"end_time": "2023-05-18T01:58:39.405299Z",
"start_time": "2023-05-18T01:58:39.395221Z"
}
}
},
{
"cell_type": "code",
"execution_count": 373,
"execution_count": 445,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 35.00%\n"
" 55.00%\n"
]
}
],
......@@ -149,8 +149,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2023-05-18T01:53:55.744380Z",
"start_time": "2023-05-18T01:53:55.740566Z"
"end_time": "2023-05-18T01:58:39.413605Z",
"start_time": "2023-05-18T01:58:39.407510Z"
}
}
}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment