sklearn usage in nature articles

sklearn_medical.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"sklearn_medical.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "modules = df[\"What is used?\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from collections import Counter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "items = Counter(modules.map(lambda x: x.split(\", \")).agg('sum'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('RF', 64),\n",
       " ('SVM', 49),\n",
       " ('LR', 36),\n",
       " ('PCA', 29),\n",
       " ('GridS', 20),\n",
       " ('TSNE', 16),\n",
       " ('AUC', 15),\n",
       " ('KNN', 13),\n",
       " ('KMeans', 12),\n",
       " ('MLP', 11),\n",
       " ('metrics', 10),\n",
       " ('StandardScaler', 8),\n",
       " ('GBT', 7),\n",
       " ('Lasso', 6),\n",
       " ('NB', 6),\n",
       " ('DBSCAN', 6),\n",
       " ('Tree', 6),\n",
       " ('ElasticNet', 5),\n",
       " ('MDS', 5),\n",
       " ('Pipeline', 5),\n",
       " ('AffinityProp', 5),\n",
       " ('LASSO', 5),\n",
       " ('cross_val_score', 4),\n",
       " ('GMM', 4),\n",
       " ('Ridge', 4),\n",
       " ('MinMaxScaler', 3),\n",
       " ('SelectKBest', 3),\n",
       " ('RFECV', 3),\n",
       " ('StratifiedKFold', 3),\n",
       " ('sihouette', 3),\n",
       " ('preprocessing', 3),\n",
       " ('LeaveOneOut', 3),\n",
       " ('LDA', 3),\n",
       " ('ShuffleSplit', 3),\n",
       " ('ExtraTree', 3),\n",
       " ('Vectorizer', 2),\n",
       " ('SpectralClustering', 2),\n",
       " ('LOO', 2),\n",
       " ('RobustScaler', 2),\n",
       " ('FastICA', 2)]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "items.most_common(40)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}