{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Classification from scratch"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"# Set CML_ROOT to root data mount point\n",
"os.environ[\"CML_ROOT\"] = \"~/mnt/rhino\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib inline\n",
"\n",
"from copy import deepcopy\n",
"from functools import partial\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import pandas as pd\n",
"from scipy.stats import zscore\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.metrics import auc, roc_auc_score, roc_curve\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"from cmlreaders import CMLReader, get_data_index\n",
"from ptsa.data.filters import ButterworthFilter, MorletWaveletFilter"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Loading data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We start by loading the data index of all RAM subjects:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"df = get_data_index(\"r1\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To train a classifier, we want to analyze record-only experiments. Here, we'll just consider FR1. Let's choose subject R1111M and see how many FR1 sessions they completed:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" subject | \n",
" experiment | \n",
" session | \n",
"
\n",
" \n",
" \n",
" \n",
" | 616 | \n",
" R1111M | \n",
" FR1 | \n",
" 0 | \n",
"
\n",
" \n",
" | 617 | \n",
" R1111M | \n",
" FR1 | \n",
" 1 | \n",
"
\n",
" \n",
" | 618 | \n",
" R1111M | \n",
" FR1 | \n",
" 2 | \n",
"
\n",
" \n",
" | 619 | \n",
" R1111M | \n",
" FR1 | \n",
" 3 | \n",
"
\n",
" \n",
"
\n",
"