{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Scatter Plots" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "UserWarning: The Dask Engine for Modin is experimental.\n", "UserWarning: The extension \"jupyterlab-plotly\" was not found and is required for Plotly-based visualizations.\n" ] } ], "source": [ "import pandas as pd\n", "import data_describe as dd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(442, 11)" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.datasets import load_diabetes\n", "data = load_diabetes()\n", "df = pd.DataFrame(data.data, columns=list(data.feature_names))\n", "df['target'] = data.target\n", "df.shape" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | age | \n", "sex | \n", "bmi | \n", "bp | \n", "s1 | \n", "s2 | \n", "s3 | \n", "s4 | \n", "s5 | \n", "s6 | \n", "target | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "0.038076 | \n", "0.050680 | \n", "0.061696 | \n", "0.021872 | \n", "-0.044223 | \n", "-0.034821 | \n", "-0.043401 | \n", "-0.002592 | \n", "0.019908 | \n", "-0.017646 | \n", "151.0 | \n", "
1 | \n", "-0.001882 | \n", "-0.044642 | \n", "-0.051474 | \n", "-0.026328 | \n", "-0.008449 | \n", "-0.019163 | \n", "0.074412 | \n", "-0.039493 | \n", "-0.068330 | \n", "-0.092204 | \n", "75.0 | \n", "