{ "cells": [ { "cell_type": "markdown", "id": "b2a7eff0-f134-4bfd-9729-604e312de968", "metadata": {}, "source": [ "# Plot - Representativeness" ] }, { "cell_type": "markdown", "id": "73a8e182-f75b-4254-9bfe-766d7a758448", "metadata": {}, "source": [ "#### Load Data" ] }, { "cell_type": "code", "execution_count": 1, "id": "89c418a3", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(467, 8) (26, 8)\n" ] } ], "source": [ "import pandas as pd\n", "\n", "df = pd.read_csv(\"../data/BaselineED_feat.csv\")\n", "gen =pd.read_csv(\"../data/GenED_feat.csv\")\n", "\n", "paper_cols = [\"log\",\"ratio_variants_per_number_of_traces\", \"ratio_most_common_variant\", 'ratio_top_10_variants', 'epa_normalized_variant_entropy', 'epa_normalized_sequence_entropy', 'epa_normalized_sequence_entropy_linear_forgetting', 'epa_normalized_sequence_entropy_exponential_forgetting'] \n", "df= df[paper_cols]\n", "\n", "print(gen.shape, df.shape)\n", "#print(gen.columns == df.columns)" ] }, { "cell_type": "code", "execution_count": 2, "id": "355f85af", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(493, 9)\n" ] }, { "data": { "text/html": [ "
\n", " | log | \n", "ratio_variants_per_number_of_traces | \n", "ratio_most_common_variant | \n", "ratio_top_10_variants | \n", "epa_normalized_variant_entropy | \n", "epa_normalized_sequence_entropy | \n", "epa_normalized_sequence_entropy_linear_forgetting | \n", "epa_normalized_sequence_entropy_exponential_forgetting | \n", "source | \n", "
---|---|---|---|---|---|---|---|---|---|
0 | \n", "BPIC16wm_p | \n", "0.002882 | \n", "0.295803 | \n", "0.714106 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "0.000000 | \n", "Real | \n", "
1 | \n", "BPIC15f5 | \n", "0.997405 | \n", "0.001730 | \n", "0.102076 | \n", "0.648702 | \n", "0.603260 | \n", "0.342410 | \n", "0.404580 | \n", "Real | \n", "
2 | \n", "BPIC15f1 | \n", "0.975813 | \n", "0.006672 | \n", "0.121768 | \n", "0.652855 | \n", "0.610294 | \n", "0.270241 | \n", "0.363928 | \n", "Real | \n", "
3 | \n", "BPIC19 | \n", "0.047562 | \n", "0.199758 | \n", "0.946368 | \n", "0.645530 | \n", "0.328029 | \n", "0.320185 | \n", "0.320282 | \n", "Real | \n", "
4 | \n", "BPIC14dia_p | \n", "0.496847 | \n", "0.037455 | \n", "0.552836 | \n", "0.774743 | \n", "0.608350 | \n", "0.305614 | \n", "0.377416 | \n", "Real | \n", "