Skip to content

Instantly share code, notes, and snippets.

@yssymmt

yssymmt/lgb01_topmml.ipynb

Created June 25, 2022 07:33
Show Gist options
  • Save yssymmt/4d0e4e683a6c7e5174262f0590638da1 to your computer and use it in GitHub Desktop.
Save yssymmt/4d0e4e683a6c7e5174262f0590638da1 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
lgb01_topmml.ipynb
{
"cells": [
{
"cell_type": "markdown",
"id": "a677a16f",
"metadata": {},
"source": [
"####PMMLモジュールのインストール"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "c0e876b0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting package metadata (current_repodata.json): ...working... done\n",
"Solving environment: ...working... done\n",
"\n",
"## Package Plan ##\n",
"\n",
" environment location: C:\\Users\\yourdirectory\\Anaconda3\n",
"\n",
" added / updated specs:\n",
" - sklearn2pmml\n",
"\n",
"\n",
"The following packages will be downloaded:\n",
"\n",
" package | build\n",
" ---------------------------|-----------------\n",
" conda-4.13.0 | py39hcbf5309_1 1.0 MB conda-forge\n",
" python_abi-3.9 | 2_cp39 4 KB conda-forge\n",
" sklearn-pandas-2.2.0 | pyhd8ed1ab_0 13 KB conda-forge\n",
" sklearn2pmml-0.81.0 | pyhd8ed1ab_0 5.9 MB conda-forge\n",
" ------------------------------------------------------------\n",
" Total: 6.9 MB\n",
"\n",
"The following NEW packages will be INSTALLED:\n",
"\n",
" python_abi conda-forge/win-64::python_abi-3.9-2_cp39\n",
" sklearn-pandas conda-forge/noarch::sklearn-pandas-2.2.0-pyhd8ed1ab_0\n",
" sklearn2pmml conda-forge/noarch::sklearn2pmml-0.81.0-pyhd8ed1ab_0\n",
"\n",
"The following packages will be UPDATED:\n",
"\n",
" conda pkgs/main::conda-4.13.0-py39haa95532_0 --> conda-forge::conda-4.13.0-py39hcbf5309_1\n",
"\n",
"\n",
"\n",
"Downloading and Extracting Packages\n",
"\n",
"python_abi-3.9 | 4 KB | | 0% \n",
"python_abi-3.9 | 4 KB | ########## | 100% \n",
"python_abi-3.9 | 4 KB | ########## | 100% \n",
"\n",
"sklearn-pandas-2.2.0 | 13 KB | | 0% \n",
"sklearn-pandas-2.2.0 | 13 KB | ########## | 100% \n",
"sklearn-pandas-2.2.0 | 13 KB | ########## | 100% \n",
"\n",
"sklearn2pmml-0.81.0 | 5.9 MB | | 0% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | | 0% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | 1 | 2% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | 2 | 3% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | 6 | 6% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | # | 11% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | #7 | 17% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | ##6 | 27% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | ###9 | 40% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | ###### | 61% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | ########8 | 89% \n",
"sklearn2pmml-0.81.0 | 5.9 MB | ########## | 100% \n",
"\n",
"conda-4.13.0 | 1.0 MB | | 0% \n",
"conda-4.13.0 | 1.0 MB | ########## | 100% \n",
"conda-4.13.0 | 1.0 MB | ########## | 100% \n",
"Preparing transaction: ...working... done\n",
"Verifying transaction: ...working... done\n",
"Executing transaction: ...working... done\n",
"\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"conda install -c conda-forge sklearn2pmml"
]
},
{
"cell_type": "markdown",
"id": "18065645",
"metadata": {},
"source": [
"####ライブラリの読み込み"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "a5ace988",
"metadata": {},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"import pandas as pd\n",
"from sqlalchemy import create_engine\n",
"import teradatasql\n",
"import teradatasqlalchemy\n",
"from sklearn.model_selection import train_test_split\n",
"import lightgbm as lgb \n",
"from sklearn.metrics import confusion_matrix\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.metrics import classification_report\n",
"from sklearn2pmml import sklearn2pmml\n",
"from sklearn2pmml.pipeline import PMMLPipeline"
]
},
{
"cell_type": "markdown",
"id": "3ecde84a",
"metadata": {},
"source": [
"####データフレームに変換"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "39c12785",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>sepal_length</th>\n",
" <th>sepal_width</th>\n",
" <th>petal_length</th>\n",
" <th>petal_width</th>\n",
" <th>targeto</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" sepal_length sepal_width petal_length petal_width targeto\n",
"0 5.1 3.5 1.4 0.2 setosa\n",
"1 4.9 3.0 1.4 0.2 setosa\n",
"2 4.7 3.2 1.3 0.2 setosa\n",
"3 4.6 3.1 1.5 0.2 setosa\n",
"4 5.0 3.6 1.4 0.2 setosa"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"iris = datasets.load_iris()\n",
"df = pd.DataFrame(iris.data, columns=iris.feature_names)\n",
"df['target'] = iris.target_names[iris.target]\n",
"df.columns = ['sepal_length','sepal_width','petal_length','petal_width','targeto']\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"id": "21ceeefc",
"metadata": {},
"source": [
"####ユニーク番号を付与、列順入替"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "ac6d8cce",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>serial_num</th>\n",
" <th>targeto</th>\n",
" <th>sepal_length</th>\n",
" <th>sepal_width</th>\n",
" <th>petal_length</th>\n",
" <th>petal_width</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>setosa</td>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>setosa</td>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>setosa</td>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>setosa</td>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>setosa</td>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" serial_num targeto sepal_length sepal_width petal_length petal_width\n",
"0 1 setosa 5.1 3.5 1.4 0.2\n",
"1 2 setosa 4.9 3.0 1.4 0.2\n",
"2 3 setosa 4.7 3.2 1.3 0.2\n",
"3 4 setosa 4.6 3.1 1.5 0.2\n",
"4 5 setosa 5.0 3.6 1.4 0.2"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"serial_num = pd.RangeIndex(start=1, stop=len(df.index) + 1, step=1)\n",
"df['serial_num'] = serial_num\n",
"df = df.loc[:,['serial_num','targeto','sepal_length','sepal_width','petal_length','petal_width']]\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"id": "d03e0a8a",
"metadata": {},
"source": [
"####Teradataへの接続、sqlalchemy エンジンを作成"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "0e5e2ee2",
"metadata": {},
"outputs": [],
"source": [
"host = \"123.456.789.0\"\n",
"user = \"jumbo\"\n",
"password = \"mambo\"\n",
"connstr = \"teradatasql://{user}:{password}@{host}\".format(host=host, user=user, password=password)\n",
"engine = create_engine(connstr)"
]
},
{
"cell_type": "markdown",
"id": "4ba3a7f2",
"metadata": {},
"source": [
"####空テーブル作成、元データ用 "
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b2a6ebb2",
"metadata": {},
"outputs": [],
"source": [
"with engine.connect() as conn:\n",
" x1 = pd.read_sql(\"\"\"\n",
" create multiset table jumbo.lgb01_iris (\n",
" serial_num integer, \n",
" targeto varchar(10) character set unicode, \n",
" sepal_length float, \n",
" sepal_width float, \n",
" petal_length float, \n",
" petal_width float \n",
" ) primary index (serial_num) \n",
" \"\"\", conn)"
]
},
{
"cell_type": "markdown",
"id": "ae1aeddf",
"metadata": {},
"source": [
"####元データの格納"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "59fbe566",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.to_sql('lgb01_iris',engine,if_exists='append',index=False)"
]
},
{
"cell_type": "markdown",
"id": "4ee90be4",
"metadata": {},
"source": [
"####格納を確認 "
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "12ca1153",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>serial_num</th>\n",
" <th>targeto</th>\n",
" <th>sepal_length</th>\n",
" <th>sepal_width</th>\n",
" <th>petal_length</th>\n",
" <th>petal_width</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>setosa</td>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>setosa</td>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>setosa</td>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>setosa</td>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>setosa</td>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>145</th>\n",
" <td>146</td>\n",
" <td>virginica</td>\n",
" <td>6.7</td>\n",
" <td>3.0</td>\n",
" <td>5.2</td>\n",
" <td>2.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>147</td>\n",
" <td>virginica</td>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>5.0</td>\n",
" <td>1.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>148</td>\n",
" <td>virginica</td>\n",
" <td>6.5</td>\n",
" <td>3.0</td>\n",
" <td>5.2</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>149</td>\n",
" <td>virginica</td>\n",
" <td>6.2</td>\n",
" <td>3.4</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>149</th>\n",
" <td>150</td>\n",
" <td>virginica</td>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>5.1</td>\n",
" <td>1.8</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>150 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" serial_num targeto sepal_length sepal_width petal_length \\\n",
"0 1 setosa 5.1 3.5 1.4 \n",
"1 2 setosa 4.9 3.0 1.4 \n",
"2 3 setosa 4.7 3.2 1.3 \n",
"3 4 setosa 4.6 3.1 1.5 \n",
"4 5 setosa 5.0 3.6 1.4 \n",
".. ... ... ... ... ... \n",
"145 146 virginica 6.7 3.0 5.2 \n",
"146 147 virginica 6.3 2.5 5.0 \n",
"147 148 virginica 6.5 3.0 5.2 \n",
"148 149 virginica 6.2 3.4 5.4 \n",
"149 150 virginica 5.9 3.0 5.1 \n",
"\n",
" petal_width \n",
"0 0.2 \n",
"1 0.2 \n",
"2 0.2 \n",
"3 0.2 \n",
"4 0.2 \n",
".. ... \n",
"145 2.3 \n",
"146 1.9 \n",
"147 2.0 \n",
"148 2.3 \n",
"149 1.8 \n",
"\n",
"[150 rows x 6 columns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"with engine.connect() as conn:\n",
" x2 = pd.read_sql(\"\"\"\n",
" select * from jumbo.lgb01_iris order by 1 \n",
" \"\"\", conn)\n",
"x2"
]
},
{
"cell_type": "markdown",
"id": "ded7ca2b",
"metadata": {},
"source": [
"####説明変数と結果変数"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "b2121799",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>sepal_length</th>\n",
" <th>sepal_width</th>\n",
" <th>petal_length</th>\n",
" <th>petal_width</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" sepal_length sepal_width petal_length petal_width\n",
"0 5.1 3.5 1.4 0.2\n",
"1 4.9 3.0 1.4 0.2\n",
"2 4.7 3.2 1.3 0.2\n",
"3 4.6 3.1 1.5 0.2\n",
"4 5.0 3.6 1.4 0.2"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X = x2.drop(['serial_num','targeto'], axis=1)\n",
"y = x2['targeto'].values\n",
"X.head()"
]
},
{
"cell_type": "markdown",
"id": "3ce30c3e",
"metadata": {},
"source": [
"####学習用、評価用への分割"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "67dbcc4a",
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=1)"
]
},
{
"cell_type": "markdown",
"id": "e6f92255",
"metadata": {},
"source": [
"####学習"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "d0df4d2c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"LGBMClassifier()"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = lgb.LGBMClassifier() \n",
"model.fit(X_train, y_train) "
]
},
{
"cell_type": "markdown",
"id": "cf6270aa",
"metadata": {},
"source": [
"####評価データの予測"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "752d7448",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['setosa', 'versicolor', 'versicolor', 'setosa', 'virginica',\n",
" 'versicolor', 'virginica', 'setosa', 'setosa', 'virginica',\n",
" 'versicolor', 'setosa', 'virginica', 'versicolor', 'versicolor',\n",
" 'setosa', 'versicolor', 'versicolor', 'setosa', 'setosa',\n",
" 'versicolor', 'versicolor', 'virginica', 'setosa', 'virginica',\n",
" 'versicolor', 'setosa', 'setosa', 'versicolor', 'virginica',\n",
" 'versicolor', 'virginica', 'versicolor', 'virginica', 'virginica',\n",
" 'setosa', 'versicolor', 'setosa', 'versicolor', 'virginica',\n",
" 'virginica', 'setosa', 'versicolor', 'virginica', 'versicolor'],\n",
" dtype=object)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"y_pred = model.predict(X_test)\n",
"y_pred"
]
},
{
"cell_type": "markdown",
"id": "f540de3c",
"metadata": {},
"source": [
"####評価データの予測確率"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "aadd968f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[9.99845068e-01, 1.54432218e-04, 4.99580208e-07],\n",
" [1.16351280e-03, 9.97668427e-01, 1.16806052e-03],\n",
" [2.39895684e-05, 9.94308872e-01, 5.66713798e-03],\n",
" [9.99951626e-01, 4.78728226e-05, 5.00792579e-07],\n",
" [6.32669869e-04, 6.39808284e-04, 9.98727522e-01],\n",
" [2.22526484e-04, 9.99538736e-01, 2.38737663e-04],\n",
" [7.59269593e-05, 1.22460832e-03, 9.98699465e-01],\n",
" [9.80755450e-01, 1.91575712e-02, 8.69787297e-05],\n",
" [9.99967609e-01, 3.18858996e-05, 5.04938586e-07],\n",
" [1.38078909e-04, 6.40124928e-04, 9.99221796e-01],\n",
" [7.05289192e-06, 9.99906324e-01, 8.66228872e-05],\n",
" [9.99951633e-01, 4.78728229e-05, 4.93949848e-07],\n",
" [1.74173849e-06, 1.98199322e-05, 9.99978438e-01],\n",
" [8.24526593e-05, 9.99751836e-01, 1.65711714e-04],\n",
" [4.59102552e-06, 9.99820763e-01, 1.74645565e-04],\n",
" [9.99967606e-01, 3.18858995e-05, 5.07881523e-07],\n",
" [4.56149536e-06, 9.99938450e-01, 5.69887569e-05],\n",
" [4.53029899e-05, 9.98287460e-01, 1.66723741e-03],\n",
" [9.99951626e-01, 4.78728226e-05, 5.00792579e-07],\n",
" [9.99967263e-01, 3.22367235e-05, 5.00211245e-07],\n",
" [8.46608214e-06, 9.99875679e-01, 1.15855232e-04],\n",
" [5.05433898e-05, 9.98045139e-01, 1.90431792e-03],\n",
" [2.29919926e-06, 2.63612702e-05, 9.99971340e-01],\n",
" [9.99967263e-01, 3.22367235e-05, 5.00211245e-07],\n",
" [1.37143803e-04, 6.40125527e-04, 9.99222731e-01],\n",
" [7.99860194e-06, 9.99751919e-01, 2.40082849e-04],\n",
" [9.99951626e-01, 4.78728226e-05, 5.00792579e-07],\n",
" [9.99967262e-01, 3.22367235e-05, 5.00800410e-07],\n",
" [2.81104395e-05, 9.95825634e-01, 4.14625563e-03],\n",
" [5.12052964e-06, 7.39520948e-05, 9.99920927e-01],\n",
" [2.52164108e-05, 9.95893607e-01, 4.08117635e-03],\n",
" [1.74165945e-06, 1.98199322e-05, 9.99978438e-01],\n",
" [6.11465116e-06, 9.99916377e-01, 7.75087568e-05],\n",
" [1.73615648e-06, 1.98199323e-05, 9.99978444e-01],\n",
" [5.83830969e-06, 1.77964109e-04, 9.99816198e-01],\n",
" [9.99951626e-01, 4.78728226e-05, 5.00792579e-07],\n",
" [4.53392657e-06, 9.99937967e-01, 5.74991400e-05],\n",
" [9.99951626e-01, 4.78728226e-05, 5.00792579e-07],\n",
" [2.56668004e-05, 9.93427955e-01, 6.54637770e-03],\n",
" [3.82630086e-06, 5.56021727e-05, 9.99940572e-01],\n",
" [1.74178131e-06, 1.98199322e-05, 9.99978438e-01],\n",
" [9.99967262e-01, 3.22367235e-05, 5.00800410e-07],\n",
" [2.38760325e-04, 9.63842806e-01, 3.59184340e-02],\n",
" [1.72547641e-06, 1.98199326e-05, 9.99978455e-01],\n",
" [2.49292497e-05, 9.94982107e-01, 4.99296385e-03]])"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"y_pred_prob = model.predict_proba(X_test)\n",
"y_pred_prob"
]
},
{
"cell_type": "markdown",
"id": "d5cc91ee",
"metadata": {},
"source": [
"####混合行列"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "1e207007",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[14, 0, 0],\n",
" [ 0, 17, 1],\n",
" [ 0, 1, 12]], dtype=int64)"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cm = confusion_matrix(y_test, y_pred)\n",
"cm"
]
},
{
"cell_type": "markdown",
"id": "797d26ed",
"metadata": {},
"source": [
"####精度、正解率"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "dfa71f9a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.9555555555555556"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ac = accuracy_score(y_test, y_pred)\n",
"ac"
]
},
{
"cell_type": "markdown",
"id": "f21c8d60",
"metadata": {},
"source": [
"####性能評価レポート"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "e2dd86fb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" setosa 1.00 1.00 1.00 14\n",
" versicolor 0.94 0.94 0.94 18\n",
" virginica 0.92 0.92 0.92 13\n",
"\n",
" accuracy 0.96 45\n",
" macro avg 0.96 0.96 0.96 45\n",
"weighted avg 0.96 0.96 0.96 45\n",
"\n"
]
}
],
"source": [
"clrp = classification_report(y_test, y_pred)\n",
"print(clrp)"
]
},
{
"cell_type": "markdown",
"id": "37800f6c",
"metadata": {},
"source": [
"####pmmlでのモデル作成"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "05a7405f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"PMMLPipeline(steps=[('classifier', LGBMClassifier())])"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"clf = PMMLPipeline(\n",
" [\n",
" (\n",
" \"classifier\",\n",
" lgb.LGBMClassifier(),\n",
" )\n",
" ]\n",
")\n",
"\n",
"clf.fit(X_train, y_train)"
]
},
{
"cell_type": "markdown",
"id": "c07dc4f3",
"metadata": {},
"source": [
"####pmmlファイルのオフロード"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "46e95e30",
"metadata": {},
"outputs": [],
"source": [
"sklearn2pmml(clf, \"lgbm_model.pmml\", with_repr=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment