{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# `GroupedPipeline`: applying a transformer per category"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"from sklearn.datasets import load_iris\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.metrics import mean_squared_error as mse, mean_absolute_error as mae\n",
"\n",
"from timeserio.data.datasets import load_iris_df\n",
"from timeserio.pipeline import GroupedPipeline\n",
"from timeserio.preprocessing import PandasValueSelector\n",
"\n",
"import seaborn as sns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load the iris dataset\n",
"\n",
"This dataset consists of four numeric and one categorical columns."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" sepal_length_cm | \n",
" sepal_width_cm | \n",
" petal_length_cm | \n",
" petal_width_cm | \n",
" species | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 5.1 | \n",
" 3.5 | \n",
" 1.4 | \n",
" 0.2 | \n",
" setosa | \n",
"
\n",
" \n",
" | 1 | \n",
" 4.9 | \n",
" 3.0 | \n",
" 1.4 | \n",
" 0.2 | \n",
" setosa | \n",
"
\n",
" \n",
"
\n",
"