Skip to content
Snippets Groups Projects
Normal view Permalink
MultinomialNBXGBoost.ipynb 419 KiB
Newer Older
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C&gt;A</td>\n",
       "      <td>ACA</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C&gt;A</td>\n",
       "      <td>ACC</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 9693 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Mutation type Trinucleotide  ALL::TARGET-10-PAIXPH-03A-01D  \\\n",
       "0           C>A           ACA                              0   \n",
       "1           C>A           ACC                              0   \n",
       "\n",
       "   ALL::TARGET-10-PAKHZT-03A-01R  ALL::TARGET-10-PAKMVD-09A-01D  \\\n",
       "0                              0                              0   \n",
       "1                              0                              0   \n",
       "\n",
       "   ALL::TARGET-10-PAKSWW-03A-01D  ALL::TARGET-10-PALETF-03A-01D  \\\n",
       "0                              1                              0   \n",
       "1                              1                              0   \n",
       "\n",
       "   ALL::TARGET-10-PALLSD-09A-01D  ALL::TARGET-10-PAMDKS-03A-01D  \\\n",
       "0                              0                              0   \n",
       "1                              0                              0   \n",
       "\n",
       "   ALL::TARGET-10-PAPJIB-04A-01D  ...  Head-SCC::V-109  Head-SCC::V-112  \\\n",
       "0                              2  ...                0                0   \n",
       "1                              0  ...                1                0   \n",
       "\n",
       "   Head-SCC::V-116  Head-SCC::V-119  Head-SCC::V-123  Head-SCC::V-124  \\\n",
       "0                0                0                0                0   \n",
       "1                0                0                0                0   \n",
       "\n",
       "   Head-SCC::V-125  Head-SCC::V-14  Head-SCC::V-29  Head-SCC::V-98  \n",
       "0                0               0               0               1  \n",
       "1                0               1               0               0  \n",
       "\n",
       "[2 rows x 9693 columns]"
      ]
     },
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1088 
     "execution_count": 418,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "other_wes_mut = pd.read_csv(\"./project_data/catalogs/WES/WES_Other.96.csv\")\n",
    "other_wes_mut.head(2)"
   ]
  },
  {
   "cell_type": "code",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1100 
   "execution_count": 419,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Cancer Types</th>\n",
       "      <th>Sample Names</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>SBS1</th>\n",
       "      <th>SBS2</th>\n",
       "      <th>SBS3</th>\n",
       "      <th>SBS4</th>\n",
       "      <th>SBS5</th>\n",
       "      <th>SBS6</th>\n",
       "      <th>SBS7a</th>\n",
       "      <th>...</th>\n",
       "      <th>SBS51</th>\n",
       "      <th>SBS52</th>\n",
       "      <th>SBS53</th>\n",
       "      <th>SBS54</th>\n",
       "      <th>SBS55</th>\n",
       "      <th>SBS56</th>\n",
       "      <th>SBS57</th>\n",
       "      <th>SBS58</th>\n",
       "      <th>SBS59</th>\n",
       "      <th>SBS60</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ALL</td>\n",
       "      <td>TARGET-10-PAIXPH-03A-01D</td>\n",
       "      <td>0.529</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ALL</td>\n",
       "      <td>TARGET-10-PAKHZT-03A-01R</td>\n",
       "      <td>0.696</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 68 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Cancer Types              Sample Names  Accuracy  SBS1  SBS2  SBS3  SBS4  \\\n",
       "0          ALL  TARGET-10-PAIXPH-03A-01D     0.529     0     0     0     0   \n",
       "1          ALL  TARGET-10-PAKHZT-03A-01R     0.696     0     0     0     0   \n",
       "\n",
       "   SBS5  SBS6  SBS7a  ...  SBS51  SBS52  SBS53  SBS54  SBS55  SBS56  SBS57  \\\n",
       "0     0     0      0  ...      0      0      0      1      0      0      0   \n",
       "1     0     0      0  ...      0      0      0      1      0      0      0   \n",
       "\n",
       "   SBS58  SBS59  SBS60  \n",
       "0      0      0      0  \n",
       "1      0      0      0  \n",
       "\n",
       "[2 rows x 68 columns]"
      ]
     },
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1217 
     "execution_count": 419,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "other_wes_act = pd.read_csv(\"./project_data/activities/WES/WES_Other.activities.csv\")\n",
    "other_wes_act.head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Imports and helpers"
   ]
  },
  {
   "cell_type": "code",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1236 
   "execution_count": 420,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import sklearn\n",
    "from sklearn.decomposition import PCA\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "#import torch \n",
    "\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import roc_auc_score\n",
    "from sklearn.metrics import roc_curve\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "from sklearn.model_selection import cross_val_score, train_test_split, KFold\n",
    "from sklearn.model_selection import StratifiedShuffleSplit\n",
    "from sklearn.model_selection import StratifiedKFold, GridSearchCV\n",
    "from sklearn.model_selection import learning_curve\n",
    "\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "# These ones are work in progress\n",
    "def plot_roc_auc(X_tst, y_test, model, is_multi_class=False):\n",
    "    probs = model.predict_proba(X_tst)\n",
    "    probs = probs[:, 1]\n",
    "    if is_multi_class:\n",
    "        auc = roc_auc_score(y_test, probs, multi_class='ovo')\n",
    "    else:\n",
    "        auc = roc_auc_score(y_test, probs, multi_class='ovo')\n",
    "    \n",
    "    fp_rate, tp_rate, thresholds = roc_curve(y_test, probs)\n",
    "    \n",
    "    plt.figure(figsize=(7,6))\n",
    "    plt.axis('scaled')\n",
    "    plt.xlim([0,1])\n",
    "    plt.ylim([0,1])\n",
    "    plt.title(\"AUC & ROC\")\n",
    "    plt.plot(fp_rate, tp_rate, 'g')\n",
    "    plt.fill_between(fp_rate, tp_rate, facecolor = \"green\", alpha = 0.7)\n",
    "    plt.text(0.95, 0.05, f'AUC = {auc}', ha='right', fontsize=12, weight='bold', color='blue')\n",
    "    plt.xlabel(\"False Positive Rate\")\n",
    "    plt.ylabel(\"True Positive Rate\")\n",
    "\n",
    "def plot_confusion_mat(y_test, y_pred, labs=None, size=None):\n",
    "    cm = sklearn.metrics.confusion_matrix(y_test, y_pred)\n",
    "    if size is None:\n",
    "        plt.figure(figsize=(12,10))\n",
    "    else:\n",
    "        plt.figure(figsize=size)\n",
    "    if labs is None:\n",
    "        sns.heatmap(cm, square=False, annot=True, fmt='d', cmap='viridis', cbar=True)\n",
    "    else:\n",
    "        sns.heatmap(cm, square=False, annot=True, fmt='d', cmap='viridis', xticklabels=labs, yticklabels=labs, cbar=True)\n",
    "    plt.xlabel('Predicted label')\n",
    "    plt.ylabel('True label')\n",
    "    #plt.ylim(0, 2)\n",
    "\n",
    "def plot_learning_curve(model, X, y):\n",
    "    N, train_lc, val_lc = learning_curve(model, X, y, cv=7, train_sizes=np.linspace(0.3, 1, 25))\n",
    "    plt.figure(figsize=(7,6))\n",
    "    plt.title(\"Learning curve\")\n",
    "    plt.plot(N, np.mean(train_lc, 1), color='blue', label='training score')\n",
    "    plt.plot(N, np.mean(val_lc, 1), color='red', label='validation score')\n",
    "    #plt.hlines(N, np.mean([train_lc[-1],  val_lc[-1]]), N[0], N[-1], color='gray', label='mean', linestyle='dashed')\n",
    "\n",
    "def plot_trn_tst_dist(y_all, y_train, y_test, y_pred, in_cols=False):\n",
    "    #fig = None\n",
    "    #ax = None\n",
    "    if in_cols:\n",
    "        fig, ax = plt.subplots(2,2)\n",
    "    else:\n",
    "        fig, ax = plt.subplots(4,1)\n",
    "\n",
    "    fig.set_size_inches(15,8)\n",
    "\n",
    "    plt_sets = [y_all, y_train, y_test, y_pred]\n",
    "    plt_labels = [\"All\", \"Train\", \"Test\", \"Pred\"]\n",
    "    plt_set_df = pd.DataFrame()\n",
    "    for i in range(len(plt_sets)):\n",
    "        s = pd.Series(plt_sets[i]).value_counts().sort_index()\n",
    "        plt_set_df[plt_labels[i]] = s\n",
    "    \n",
    "        pd.DataFrame({plt_labels[i]: s}).plot(ax=ax.flat[i], kind=\"bar\")\n",
    "        #sns.countplot(x=s, \n",
    "        #            palette=sns.hls_palette(2),\n",
    "        #            ax=ax[i])\n",
    "        ax.flat[i].tick_params(axis=\"x\", rotation=90)\n",
    "\n",
    "    fig.tight_layout()\n",
    "    with pd.option_context('display.max_rows', None,\n",
    "                       'display.max_columns', None,\n",
    "                       'display.precision', 2,\n",
    "                       ):\n",
    "        print(plt_set_df)\n",
    "\n",
    "\n",
    "   \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Dataset preprocess, combine profile data to a single data frame\n",
    "\n",
    "From all profile sets, a combined data frame is made, which has samples in the rows and features in the columns."
   ]
  },
  {
   "cell_type": "code",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1352 
   "execution_count": 421,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Profile data:\n",
      "\n",
      "---Data set diagnostics print---\n",
      "\n",
      "Missing entries in mutations: 0\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1364 
      "The shape of the mutations data frame (20343, 97)\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1365 
      "Checking normalization: sum of some rows:\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1366 1367 1368 1369 1370 
      " cancer::TK74_LCIS2    1.0\n",
      "RCC::TCGA             1.0\n",
      "AdenoCA::TCGA         1.0\n",
      "AdenoCA::TCGA         1.0\n",
      "Melanoma::TCGA        1.0\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1371 1372 1373 
      "dtype: float64\n",
      "\n",
      "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 
      "Tumor counts:\n",
      " AdenoCA      7712\n",
      "SCC          2188\n",
      "cancer       1639\n",
      "HCC          1318\n",
      "Melanoma     1231\n",
      "BNHL          822\n",
      "RCC           775\n",
      "GBM           605\n",
      "Medullo       557\n",
      "CA            462\n",
      "cell          389\n",
      "CMDI          357\n",
      "LGG           326\n",
      "CLL           302\n",
      "Papillary     297\n",
      "neoplasm      247\n",
      "ALL           240\n",
      "Ewings        231\n",
      "AML           230\n",
      "30            212\n",
      "bone          203\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1396 1397 1398 
      "Name: tumor_types, dtype: int64\n",
      "\n",
      "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1399 1400 1401 1402 1403 1404 1405 1406 1407 
      "Tumor types with smallish counts: 7\n",
      "Papillary    297\n",
      "neoplasm     247\n",
      "ALL          240\n",
      "Ewings       231\n",
      "AML          230\n",
      "30           212\n",
      "bone         203\n",
      "Name: tumor_types, dtype: int64\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1408 1409 
      "\n",
      "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1410 1411 
      "Unique tumor types:  21\n",
      "['30', 'ALL', 'AML', 'AdenoCA', 'BNHL', 'CA', 'CLL', 'CMDI', 'Ewings', 'GBM', 'HCC', 'LGG', 'Medullo', 'Melanoma', 'Papillary', 'RCC', 'SCC', 'bone', 'cancer', 'cell', 'neoplasm']\n"
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 
     ]
    }
   ],
   "source": [
    "\n",
    "def prepare_mut_df(raw_mutation_dfs, is_profile, small_sample_limit=None):\n",
    "\n",
    "    mutations_all = pd.DataFrame()\n",
    "\n",
    "    for df in raw_mutation_dfs:\n",
    "        # Make a copy of the original data frame and start processing from there\n",
    "        mutations  = df.copy()\n",
    "    \n",
    "        if is_profile:\n",
    "            mutations['mut_tri'] = mutations.apply(lambda a: '{}_{}'.format(a['Mutation type'], a['Trinucleotide']), axis=1)\n",
    "            mutations = mutations.set_index('mut_tri').drop(['Mutation type', 'Trinucleotide'], axis=1)\n",
    "            mutations = mutations.T\n",
    "        else:\n",
    "            mutations['mut_tri'] = mutations.apply(lambda a: '{}::{}'.format(a['Cancer Types'], a['Sample Names']), axis=1)\n",
    "            mutations = mutations.set_index('mut_tri').drop(['Cancer Types', 'Sample Names', 'Accuracy'], axis=1)\n",
    "     \n",
    "        # Rename some index names\n",
    "        renamed_items = list(mutations.index)\n",
    "        index_items = list(mutations.index)\n",
    "\n",
    "        # Combine rows for low count labels\n",
    "        for i in range(len(index_items)):\n",
    "            result = index_items[i]\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1440 1441 1442 1443 1444 1445 1446 1447 1448 
    "            parts = result.split('-')\n",
    "            if len(parts) > 1:\n",
    "                result = parts[1]\n",
    "            else:\n",
    "                result = parts[0]\n",
    "            \n",
    "            #result = result.split('-')[0]\n",
    "            #for to_sub in ['Adeno', 'Bone', 'Breast', 'Cervix', 'CNS', 'Eye', 'Liver', 'Lymph', 'Lung', 'Kidney', 'Myeloid', 'Panc' ]:\n",
    "            #    result = re.sub( to_sub + r'(-\\w*)', to_sub, result)\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 
    "                \n",
    "            renamed_items[i] = result.replace('Ca', 'CA')\n",
    "       \n",
    "        mutations.rename(index=dict(zip(index_items, renamed_items)), inplace = True)\n",
    "   \n",
    "        # Normalize \n",
    "        row_sums = mutations.sum(axis=1)\n",
    "        mutations = mutations.divide(row_sums, axis = 0)\n",
    "\n",
    "        mutations_all = pd.concat([mutations_all, mutations])\n",
    "\n",
    "    mutations_all.sort_index(inplace=True)\n",
    "\n",
    "    # Do we need to renormalize after obtaining the full dataframe?\n",
    "  \n",
    "    # Figure out tumor types based on the first part of the index\n",
    "    tumor_types = [a.split(':')[0] for a in mutations_all.index]\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1466 1467 
    "    \n",
    "    #print(\"ttt\", tumor_types)\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1468 1469 1470 1471 
    "    mutations_all[\"tumor_types\"] = tumor_types\n",
    "\n",
    "    # Get rid of types with very few samples if the limit is specified\n",
    "    if small_sample_limit is not None:\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1472 1473 1474 
    "        mutations_all = cull_small_sample_counts(mutations_all, small_sample_limit)\n",
    "\n",
    "    tumor_types = mutations_all[\"tumor_types\"] \n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1475 
    "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1476 1477 1478 
    "    # Prepare a list with all the types appearing only once\n",
    "    unique_tumor_types = sorted(list(set(tumor_types)))\n",
    "    # Attach this back to the frame\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1479 1480 1481 
    "    \n",
    "    return (mutations_all, unique_tumor_types)\n",
    "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1482 1483 1484 1485 1486 1487 1488 1489 
    "def cull_small_sample_counts(mutations, small_sample_limit):\n",
    "    \n",
    "    counts = mutations[\"tumor_types\"].value_counts()\n",
    "    big_counts = counts[list(counts > small_sample_limit)]\n",
    "    big_index = mutations[\"tumor_types\"].isin(list(big_counts.index))\n",
    "    mutations = mutations[big_index]\n",
    "\n",
    "    return mutations\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 
    "\n",
    "def print_dset_diag(mut_df, unique_tumor_types, small_sample_limit):\n",
    "    # Check if the data frame is ok\n",
    "    print(\"\\n---Data set diagnostics print---\\n\")\n",
    "    print(\"Missing entries in mutations:\", mut_df.isnull().sum().sum())\n",
    "    print(\"The shape of the mutations data frame\", mut_df.shape)\n",
    "\n",
    "    # Check to see if the rows are normalized to one, take a sample from the data frame\n",
    "    norm_df = mut_df.sample(n=5, random_state=5)\n",
    "    print(\"Checking normalization: sum of some rows:\\n\", norm_df.iloc[:,0:-1].sum(axis=1))\n",
    "    print(\"\\n\")\n",
    "\n",
    "    # Check some counts of tumor types\n",
    "    tumor_counts = mut_df[\"tumor_types\"].value_counts() #.sort_values(ascending=True)\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1504 
    "    print(\"Tumor counts:\\n\", tumor_counts)\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 
    "    print(\"\\n\")\n",
    "\n",
    "    small_counts = tumor_counts < 1.5*small_sample_limit\n",
    "    print(\"Tumor types with smallish counts:\",  sum(small_counts))\n",
    "\n",
    "    print(tumor_counts[small_counts])\n",
    "    print(\"\\n\")\n",
    "\n",
    "    # Tumor types\n",
    "    print(\"Unique tumor types: \", len(unique_tumor_types))\n",
    "    print(unique_tumor_types)\n",
    "\n",
    "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1518 
    "small_sample_limit = 250\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 
    "\n",
    "profile_raw_data_sets = [PCAWG_wgs_mut, TCGA_wes_mut, nonPCAWG_wgs_mut, other_wes_mut]\n",
    "profile_mut_all, prf_unique_tumor_types = prepare_mut_df(profile_raw_data_sets, True, small_sample_limit)\n",
    "\n",
    "# Print some diagnostics from the prepared data set\n",
    "print(\"Profile data:\")\n",
    "print_dset_diag(profile_mut_all, prf_unique_tumor_types, small_sample_limit)\n",
    "\n",
    "# Data matrix X for fitting, omit the tumor labeling from there, use that information in constructing true y\n",
    "# Note: this contains profile data only\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1529 
    "#X_prf = profile_mut_all.drop(\"tumor_types\", axis=1)"
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Dataset preprocess for activites data"
   ]
  },
  {
   "cell_type": "code",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1541 
   "execution_count": 422,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Activities data:\n",
      "\n",
      "---Data set diagnostics print---\n",
      "\n",
      "Missing entries in mutations: 0\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1553 
      "The shape of the mutations data frame (20343, 66)\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1554 1555 
      "Checking normalization: sum of some rows:\n",
      " mut_tri\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1556 1557 1558 1559 1560 
      "cancer::TK74_LCIS2    1.0\n",
      "RCC::TCGA             1.0\n",
      "AdenoCA::TCGA         1.0\n",
      "AdenoCA::TCGA         1.0\n",
      "Melanoma::TCGA        1.0\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1561 1562 1563 
      "dtype: float64\n",
      "\n",
      "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 
      "Tumor counts:\n",
      " AdenoCA      7712\n",
      "SCC          2188\n",
      "cancer       1639\n",
      "HCC          1318\n",
      "Melanoma     1231\n",
      "BNHL          822\n",
      "RCC           775\n",
      "GBM           605\n",
      "Medullo       557\n",
      "CA            462\n",
      "cell          389\n",
      "CMDI          357\n",
      "LGG           326\n",
      "CLL           302\n",
      "Papillary     297\n",
      "neoplasm      247\n",
      "ALL           240\n",
      "Ewings        231\n",
      "AML           230\n",
      "30            212\n",
      "bone          203\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1586 1587 1588 
      "Name: tumor_types, dtype: int64\n",
      "\n",
      "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1589 1590 1591 1592 1593 1594 1595 1596 1597 
      "Tumor types with smallish counts: 7\n",
      "Papillary    297\n",
      "neoplasm     247\n",
      "ALL          240\n",
      "Ewings       231\n",
      "AML          230\n",
      "30           212\n",
      "bone         203\n",
      "Name: tumor_types, dtype: int64\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1598 1599 
      "\n",
      "\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1600 1601 
      "Unique tumor types:  21\n",
      "['30', 'ALL', 'AML', 'AdenoCA', 'BNHL', 'CA', 'CLL', 'CMDI', 'Ewings', 'GBM', 'HCC', 'LGG', 'Medullo', 'Melanoma', 'Papillary', 'RCC', 'SCC', 'bone', 'cancer', 'cell', 'neoplasm']\n"
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 
     ]
    }
   ],
   "source": [
    "act_raw_data_sets = [PCAWG_wgs_act, TCGA_wes_act, nonPCAWG_wgs_act, other_wes_act]\n",
    "act_mut_all, act_unique_tumor_types = prepare_mut_df(act_raw_data_sets, is_profile=False, small_sample_limit=small_sample_limit)\n",
    "\n",
    "# Print some diagnostics from the prepared data set\n",
    "print(\"Activities data:\")\n",
    "print_dset_diag(act_mut_all, act_unique_tumor_types, small_sample_limit)\n",
    "\n",
    "# Data matrix X for fitting, omit the tumor labeling from there, use that information in constructing true y\n",
    "# Note: this contains profile data only\n",
    "X_act = act_mut_all.drop(\"tumor_types\", axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Check profile data content"
   ]
  },
  {
   "cell_type": "code",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1627 
   "execution_count": 423,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Some content from the full profile set:\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>mut_tri</th>\n",
       "      <th>C&gt;A_ACA</th>\n",
       "      <th>C&gt;A_ACC</th>\n",
       "      <th>C&gt;A_ACG</th>\n",
       "      <th>C&gt;A_ACT</th>\n",
       "      <th>C&gt;A_CCA</th>\n",
       "      <th>C&gt;A_CCC</th>\n",
       "      <th>C&gt;A_CCG</th>\n",
       "      <th>C&gt;A_CCT</th>\n",
       "      <th>C&gt;A_GCA</th>\n",
       "      <th>C&gt;A_GCC</th>\n",
       "      <th>...</th>\n",
       "      <th>T&gt;G_CTT</th>\n",
       "      <th>T&gt;G_GTA</th>\n",
       "      <th>T&gt;G_GTC</th>\n",
       "      <th>T&gt;G_GTG</th>\n",
       "      <th>T&gt;G_GTT</th>\n",
       "      <th>T&gt;G_TTA</th>\n",
       "      <th>T&gt;G_TTC</th>\n",
       "      <th>T&gt;G_TTG</th>\n",
       "      <th>T&gt;G_TTT</th>\n",
       "      <th>tumor_types</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 
       "      <th>30</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.000000</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1694 
       "      <td>...</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1695 
       "      <td>0.00</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1696 1697 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1698 
       "      <td>0.1</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1699 1700 1701 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1702 
       "      <td>0.00</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1703 
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1704 
       "      <td>30</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1705 1706 
       "    </tr>\n",
       "    <tr>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1707 1708 
       "      <th>30</th>\n",
       "      <td>0.040000</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1709 1710 
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1711 1712 1713 1714 1715 1716 
       "      <td>0.02</td>\n",
       "      <td>0.08</td>\n",
       "      <td>0.020000</td>\n",
       "      <td>0.020000</td>\n",
       "      <td>0.040000</td>\n",
       "      <td>0.140000</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1717 
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1718 1719 
       "      <td>...</td>\n",
       "      <td>0.04</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1720 1721 1722 1723 1724 1725 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1726 1727 1728 
       "      <td>0.02</td>\n",
       "      <td>0.0</td>\n",
       "      <td>30</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1729 1730 
       "    </tr>\n",
       "    <tr>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1731 1732 
       "      <th>30</th>\n",
       "      <td>0.153846</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1733 1734 
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1735 1736 1737 
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.076923</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1738 
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1739 1740 
       "      <td>0.076923</td>\n",
       "      <td>0.076923</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1741 
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1742 1743 
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1744 1745 1746 1747 1748 1749 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1750 
       "      <td>0.00</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1751 
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1752 1753 1754 1755 
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1756 
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1757 1758 1759 1760 
       "      <td>0.032258</td>\n",
       "      <td>0.032258</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1761 
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1762 1763 1764 1765 
       "      <td>0.032258</td>\n",
       "      <td>0.032258</td>\n",
       "      <td>0.032258</td>\n",
       "      <td>0.032258</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1766 
       "      <td>...</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1767 
       "      <td>0.00</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1768 1769 1770 1771 1772 1773 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1774 1775 1776 
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>30</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1777 1778 
       "    </tr>\n",
       "    <tr>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1779 1780 1781 1782 1783 1784 1785 
       "      <th>30</th>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.000000</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1786 1787 1788 1789 
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1790 1791 
       "      <td>...</td>\n",
       "      <td>0.00</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1792 1793 1794 1795 1796 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1797 1798 1799 1800 
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>30</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1801 1802 1803 1804 1805 1806 1807 
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 97 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 
       "mut_tri   C>A_ACA   C>A_ACC   C>A_ACG  C>A_ACT  C>A_CCA   C>A_CCC   C>A_CCG  \\\n",
       "30       0.000000  0.000000  0.000000     0.00     0.00  0.000000  0.000000   \n",
       "30       0.040000  0.000000  0.000000     0.02     0.08  0.020000  0.020000   \n",
       "30       0.153846  0.000000  0.000000     0.00     0.00  0.076923  0.000000   \n",
       "30       0.000000  0.032258  0.032258     0.00     0.00  0.000000  0.032258   \n",
       "30       0.100000  0.100000  0.000000     0.00     0.00  0.000000  0.000000   \n",
       "\n",
       "mut_tri   C>A_CCT   C>A_GCA   C>A_GCC  ...  T>G_CTT  T>G_GTA  T>G_GTC  \\\n",
       "30       0.100000  0.100000  0.000000  ...     0.00      0.0      0.0   \n",
       "30       0.040000  0.140000  0.000000  ...     0.04      0.0      0.0   \n",
       "30       0.076923  0.076923  0.000000  ...     0.00      0.0      0.0   \n",
       "30       0.032258  0.032258  0.032258  ...     0.00      0.0      0.0   \n",
       "30       0.000000  0.000000  0.000000  ...     0.00      0.0      0.0   \n",
       "\n",
       "mut_tri  T>G_GTG  T>G_GTT  T>G_TTA  T>G_TTC  T>G_TTG  T>G_TTT  tumor_types  \n",
       "30           0.1      0.0      0.0      0.0     0.00      0.0           30  \n",
       "30           0.0      0.0      0.0      0.0     0.02      0.0           30  \n",
       "30           0.0      0.0      0.0      0.0     0.00      0.0           30  \n",
       "30           0.0      0.0      0.0      0.0     0.00      0.0           30  \n",
       "30           0.0      0.0      0.0      0.0     0.00      0.0           30  \n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1828 1829 1830 1831 
       "\n",
       "[5 rows x 97 columns]"
      ]
     },
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1832 
     "execution_count": 423,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(\"Some content from the full profile set:\")\n",
    "profile_mut_all.head(5)"
   ]
  },
  {
   "cell_type": "code",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1844 
   "execution_count": 424,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1845 1846 1847 1848 
   "metadata": {},
   "outputs": [
    {
     "data": {
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1849 
      "image/png": "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",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1850 1851 1852 1853 
      "text/plain": [
       "<Figure size 1800x360 with 1 Axes>"
      ]
     },
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1854 
     "metadata": {},
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(25, 5))\n",
    "sns.set_theme()\n",
    "profile_mut_all[\"tumor_types\"].value_counts().sort_index().plot(kind=\"bar\")\n",
    "#sns.countplot(x=profile_mut_all[\"tumor_types\"], palette=sns.hls_palette(2))\n",
    "plt.xticks(rotation=90);\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Check activites data content"
   ]
  },
  {
   "cell_type": "code",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1875 
   "execution_count": 425,
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Some content from the full act set:\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SBS1</th>\n",
       "      <th>SBS2</th>\n",
       "      <th>SBS3</th>\n",
       "      <th>SBS4</th>\n",
       "      <th>SBS5</th>\n",
       "      <th>SBS6</th>\n",
       "      <th>SBS7a</th>\n",
       "      <th>SBS7b</th>\n",
       "      <th>SBS7c</th>\n",
       "      <th>SBS7d</th>\n",
       "      <th>...</th>\n",
       "      <th>SBS52</th>\n",
       "      <th>SBS53</th>\n",
       "      <th>SBS54</th>\n",
       "      <th>SBS55</th>\n",
       "      <th>SBS56</th>\n",
       "      <th>SBS57</th>\n",
       "      <th>SBS58</th>\n",
       "      <th>SBS59</th>\n",
       "      <th>SBS60</th>\n",
       "      <th>tumor_types</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mut_tri</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1955 1956 1957 
       "      <th>30</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1975 1976 
       "      <td>0.0</td>\n",
       "      <td>30</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1977 1978 
       "    </tr>\n",
       "    <tr>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1979 1980 1981 
       "      <th>30</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Inital viz and multinomial naive bayes & xgboots notebooks added
jpronkko committed
1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
jpronkko's avatar
Different grouping, sample limit 250  
jpronkko committed
1999 2000 
       "      <td>0.0</td>\n",
       "      <td>30</td>\n",
Show full blame