From faac73c574f674791eb0ad063b5717b2dce10b91 Mon Sep 17 00:00:00 2001
From: shaikhiz <72118161+shaikhiz@users.noreply.github.com>
Date: Fri, 3 Feb 2023 15:32:58 -0500
Subject: [PATCH] changes to tpot max time
---
tpot_tutorial.ipynb | 253 ++++++++++++++++++++------------------------
1 file changed, 116 insertions(+), 137 deletions(-)
diff --git a/tpot_tutorial.ipynb b/tpot_tutorial.ipynb
index 63f426c..40bbf5b 100644
--- a/tpot_tutorial.ipynb
+++ b/tpot_tutorial.ipynb
@@ -10,7 +10,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 1,
"id": "eaee9fda",
"metadata": {},
"outputs": [
@@ -18,33 +18,33 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Requirement already satisfied: torch in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (1.10.2)\n",
- "Requirement already satisfied: typing-extensions in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from torch) (3.10.0.2)\n",
+ "Requirement already satisfied: torch in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (1.13.1)\n",
+ "Requirement already satisfied: typing-extensions in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from torch) (3.10.0.2)\n",
"Note: you may need to restart the kernel to use updated packages.\n",
- "Requirement already satisfied: xgboost in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (1.5.2)\n",
- "Requirement already satisfied: numpy in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from xgboost) (1.21.2)\n",
- "Requirement already satisfied: scipy in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from xgboost) (1.8.0)\n",
+ "Requirement already satisfied: xgboost in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (1.7.3)\n",
+ "Requirement already satisfied: numpy in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from xgboost) (1.21.2)\n",
+ "Requirement already satisfied: scipy in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from xgboost) (1.7.3)\n",
"Note: you may need to restart the kernel to use updated packages.\n",
- "Requirement already satisfied: tpot in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (0.11.7)\n",
- "Requirement already satisfied: xgboost>=1.1.0 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.5.2)\n",
- "Requirement already satisfied: joblib>=0.13.2 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.1.0)\n",
- "Requirement already satisfied: numpy>=1.16.3 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.21.2)\n",
- "Requirement already satisfied: stopit>=1.1.1 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.1.2)\n",
- "Requirement already satisfied: tqdm>=4.36.1 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (4.62.3)\n",
- "Requirement already satisfied: scipy>=1.3.1 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.8.0)\n",
- "Requirement already satisfied: scikit-learn>=0.22.0 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.0.1)\n",
- "Requirement already satisfied: update-checker>=0.16 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (0.18.0)\n",
- "Requirement already satisfied: deap>=1.2 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.3.1)\n",
- "Requirement already satisfied: pandas>=0.24.2 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.3.5)\n",
- "Requirement already satisfied: python-dateutil>=2.7.3 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from pandas>=0.24.2->tpot) (2.8.2)\n",
- "Requirement already satisfied: pytz>=2017.3 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from pandas>=0.24.2->tpot) (2021.3)\n",
- "Requirement already satisfied: six>=1.5 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from python-dateutil>=2.7.3->pandas>=0.24.2->tpot) (1.16.0)\n",
- "Requirement already satisfied: threadpoolctl>=2.0.0 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from scikit-learn>=0.22.0->tpot) (2.2.0)\n",
- "Requirement already satisfied: requests>=2.3.0 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from update-checker>=0.16->tpot) (2.26.0)\n",
- "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (1.26.7)\n",
- "Requirement already satisfied: charset-normalizer~=2.0.0 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2.0.4)\n",
- "Requirement already satisfied: certifi>=2017.4.17 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2021.10.8)\n",
- "Requirement already satisfied: idna<4,>=2.5 in /Users/kaitlynarnold/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (3.3)\n",
+ "Requirement already satisfied: tpot in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (0.11.7)\n",
+ "Requirement already satisfied: tqdm>=4.36.1 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (4.62.3)\n",
+ "Requirement already satisfied: xgboost>=1.1.0 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.7.3)\n",
+ "Requirement already satisfied: deap>=1.2 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.3.3)\n",
+ "Requirement already satisfied: pandas>=0.24.2 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.3.5)\n",
+ "Requirement already satisfied: update-checker>=0.16 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (0.18.0)\n",
+ "Requirement already satisfied: stopit>=1.1.1 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.1.2)\n",
+ "Requirement already satisfied: scipy>=1.3.1 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.7.3)\n",
+ "Requirement already satisfied: scikit-learn>=0.22.0 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.0.1)\n",
+ "Requirement already satisfied: joblib>=0.13.2 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.1.0)\n",
+ "Requirement already satisfied: numpy>=1.16.3 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from tpot) (1.21.2)\n",
+ "Requirement already satisfied: python-dateutil>=2.7.3 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from pandas>=0.24.2->tpot) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2017.3 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from pandas>=0.24.2->tpot) (2021.3)\n",
+ "Requirement already satisfied: six>=1.5 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from python-dateutil>=2.7.3->pandas>=0.24.2->tpot) (1.16.0)\n",
+ "Requirement already satisfied: threadpoolctl>=2.0.0 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from scikit-learn>=0.22.0->tpot) (2.2.0)\n",
+ "Requirement already satisfied: requests>=2.3.0 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from update-checker>=0.16->tpot) (2.27.1)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (3.3)\n",
+ "Requirement already satisfied: charset-normalizer~=2.0.0 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2.0.4)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (1.26.7)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /Users/izaanys/opt/anaconda3/lib/python3.8/site-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2022.9.24)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
@@ -94,7 +94,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 2,
"id": "022ab1ce",
"metadata": {},
"outputs": [],
@@ -116,7 +116,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 3,
"id": "2898aaa9",
"metadata": {},
"outputs": [
@@ -137,7 +137,7 @@
" 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]))"
]
},
- "execution_count": 4,
+ "execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
@@ -150,7 +150,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 4,
"id": "1d1ac27a",
"metadata": {},
"outputs": [
@@ -160,7 +160,7 @@
"((112, 4), (38, 4), (112,), (38,))"
]
},
- "execution_count": 5,
+ "execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -173,21 +173,14 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 5,
"id": "015515d0",
"metadata": {},
"outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Warning: xgboost.XGBClassifier is not available and will not be used by TPOT.\n"
- ]
- },
{
"data": {
"application/vnd.jupyter.widget-view+json": {
- "model_id": "49da94ec3a20499782a4a98ab6224166",
+ "model_id": "",
"version_major": 2,
"version_minor": 0
},
@@ -203,14 +196,14 @@
"output_type": "stream",
"text": [
"\n",
- "2.21 minutes have elapsed. TPOT will close down.\n",
+ "2.02 minutes have elapsed. TPOT will close down.\n",
"TPOT closed during evaluation in one generation.\n",
"WARNING: TPOT may not provide a good pipeline if TPOT is stopped/interrupted in a early generation.\n",
"\n",
"\n",
"TPOT closed prematurely. Will use the current best pipeline.\n",
"\n",
- "Best pipeline: MLPClassifier(input_matrix, alpha=0.0001, learning_rate_init=0.01)\n",
+ "Best pipeline: LogisticRegression(input_matrix, C=25.0, dual=False, penalty=l2)\n",
"0.9736842105263158\n"
]
}
@@ -220,14 +213,22 @@
"# Will report the score of the best found pipeline\n",
"# Change max_time_mins to a higher time to allow TPOT to run without interuption\n",
"# It is currently at 2 mins for sake of not taking to long\n",
- "tpot = TPOTClassifier(verbosity=2, max_time_mins=2)\n",
+ "tpot = TPOTClassifier(verbosity=2, max_time_mins=4)\n",
"tpot.fit(X_train, y_train)\n",
"print(tpot.score(X_test, y_test))"
]
},
+ {
+ "cell_type": "markdown",
+ "id": "22bb780f",
+ "metadata": {},
+ "source": [
+ "Issued warning of TPOT closed prematurely. I am increasing the max_time to 4 so tpot can completely run and the results are more accurate"
+ ]
+ },
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 6,
"id": "fedcae2c",
"metadata": {},
"outputs": [],
@@ -246,7 +247,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 7,
"id": "f2ac0eda",
"metadata": {},
"outputs": [
@@ -388,7 +389,7 @@
"4 0 373450 8.0500 NaN S "
]
},
- "execution_count": 12,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -401,7 +402,7 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 8,
"id": "30eeb3aa",
"metadata": {},
"outputs": [],
@@ -412,7 +413,7 @@
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": 9,
"id": "bcc561a3",
"metadata": {},
"outputs": [
@@ -436,7 +437,7 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 10,
"id": "5be7251f",
"metadata": {},
"outputs": [
@@ -457,7 +458,7 @@
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": 11,
"id": "8bb50fa8",
"metadata": {},
"outputs": [],
@@ -469,7 +470,7 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 12,
"id": "11c06d01",
"metadata": {},
"outputs": [
@@ -491,7 +492,7 @@
"dtype: bool"
]
},
- "execution_count": 17,
+ "execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -504,7 +505,7 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 13,
"id": "aa017a2a",
"metadata": {},
"outputs": [],
@@ -517,7 +518,7 @@
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 14,
"id": "34567d07",
"metadata": {},
"outputs": [
@@ -533,7 +534,7 @@
" [1, 0, 0, ..., 0, 0, 0]])"
]
},
- "execution_count": 19,
+ "execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
@@ -544,7 +545,7 @@
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 15,
"id": "f31db644",
"metadata": {},
"outputs": [],
@@ -555,7 +556,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 16,
"id": "e8ccd33c",
"metadata": {},
"outputs": [],
@@ -566,7 +567,7 @@
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 17,
"id": "594776f6",
"metadata": {},
"outputs": [],
@@ -578,7 +579,7 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": 18,
"id": "e8d47aef",
"metadata": {},
"outputs": [
@@ -588,7 +589,7 @@
"False"
]
},
- "execution_count": 23,
+ "execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@@ -600,7 +601,7 @@
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 19,
"id": "6fb6b7df",
"metadata": {},
"outputs": [
@@ -610,7 +611,7 @@
"156"
]
},
- "execution_count": 24,
+ "execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
@@ -621,7 +622,7 @@
},
{
"cell_type": "code",
- "execution_count": 25,
+ "execution_count": 20,
"id": "09fe6803",
"metadata": {},
"outputs": [],
@@ -632,7 +633,7 @@
},
{
"cell_type": "code",
- "execution_count": 26,
+ "execution_count": 21,
"id": "a14bb5fd",
"metadata": {},
"outputs": [
@@ -642,7 +643,7 @@
"(668, 223)"
]
},
- "execution_count": 26,
+ "execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
@@ -655,21 +656,14 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": null,
"id": "227863a0",
"metadata": {},
"outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Warning: xgboost.XGBClassifier is not available and will not be used by TPOT.\n"
- ]
- },
{
"data": {
"application/vnd.jupyter.widget-view+json": {
- "model_id": "",
+ "model_id": "986af026de044e8694da6328fcffcb1c",
"version_major": 2,
"version_minor": 0
},
@@ -679,56 +673,36 @@
},
"metadata": {},
"output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Generation 1 - Current best internal CV score: 0.8068791381438671\n",
- "\n",
- "2.01 minutes have elapsed. TPOT will close down.\n",
- "TPOT closed during evaluation in one generation.\n",
- "WARNING: TPOT may not provide a good pipeline if TPOT is stopped/interrupted in a early generation.\n",
- "\n",
- "\n",
- "TPOT closed prematurely. Will use the current best pipeline.\n",
- "\n",
- "Best pipeline: DecisionTreeClassifier(input_matrix, criterion=gini, max_depth=3, min_samples_leaf=13, min_samples_split=20)\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "TPOTClassifier(max_eval_time_mins=0.04, max_time_mins=2, population_size=40,\n",
- " verbosity=2)"
- ]
- },
- "execution_count": 27,
- "metadata": {},
- "output_type": "execute_result"
}
],
"source": [
"# create the classifier and fit the model, reports the best pipeline\n",
"# Parameters within the TPOT Classifier can be changed to allow for longer run time across more models\n",
- "tpot = TPOTClassifier(verbosity=2, max_time_mins=2, max_eval_time_mins=0.04, population_size=40)\n",
+ "tpot = TPOTClassifier(verbosity=2, max_time_mins=4, max_eval_time_mins=0.04, population_size=40)\n",
"tpot.fit(titanic_new[training_indices], titanic_class[training_indices])"
]
},
+ {
+ "cell_type": "markdown",
+ "id": "910d6e80",
+ "metadata": {},
+ "source": [
+ "Issued warning of TPOT closed prematurely. I am increasing the max_time so tpot can completely run and the results are more accurate"
+ ]
+ },
{
"cell_type": "code",
- "execution_count": 28,
+ "execution_count": 23,
"id": "ca18f35b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "0.757847533632287"
+ "0.7533632286995515"
]
},
- "execution_count": 28,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
@@ -740,7 +714,7 @@
},
{
"cell_type": "code",
- "execution_count": 29,
+ "execution_count": 24,
"id": "4d710e07",
"metadata": {},
"outputs": [],
@@ -751,7 +725,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 25,
"id": "d7ff45ed",
"metadata": {},
"outputs": [
@@ -873,7 +847,7 @@
"max 1309.000000 3.000000 76.000000 8.000000 9.000000 512.329200"
]
},
- "execution_count": 30,
+ "execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
@@ -886,7 +860,7 @@
},
{
"cell_type": "code",
- "execution_count": 31,
+ "execution_count": 26,
"id": "8264d2ed",
"metadata": {},
"outputs": [],
@@ -899,7 +873,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 27,
"id": "fe8198e3",
"metadata": {},
"outputs": [],
@@ -911,7 +885,7 @@
},
{
"cell_type": "code",
- "execution_count": 33,
+ "execution_count": 28,
"id": "13204313",
"metadata": {},
"outputs": [
@@ -932,7 +906,7 @@
"dtype: bool"
]
},
- "execution_count": 33,
+ "execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
@@ -945,7 +919,7 @@
},
{
"cell_type": "code",
- "execution_count": 34,
+ "execution_count": 29,
"id": "82e8d3fb",
"metadata": {},
"outputs": [],
@@ -960,7 +934,7 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 30,
"id": "185ba8c1",
"metadata": {},
"outputs": [],
@@ -971,7 +945,7 @@
},
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 31,
"id": "359c8b6b",
"metadata": {},
"outputs": [
@@ -981,7 +955,7 @@
"False"
]
},
- "execution_count": 36,
+ "execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
@@ -992,7 +966,7 @@
},
{
"cell_type": "code",
- "execution_count": 37,
+ "execution_count": 32,
"id": "e73a0c32",
"metadata": {},
"outputs": [],
@@ -1002,7 +976,7 @@
},
{
"cell_type": "code",
- "execution_count": 38,
+ "execution_count": 33,
"id": "d868e452",
"metadata": {},
"outputs": [],
@@ -1013,7 +987,7 @@
},
{
"cell_type": "code",
- "execution_count": 40,
+ "execution_count": 34,
"id": "1666f357",
"metadata": {},
"outputs": [
@@ -1023,7 +997,7 @@
"array([0, 1, 0, 0, 1, 0, 1, 0, 1, 0])"
]
},
- "execution_count": 40,
+ "execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
@@ -1034,10 +1008,26 @@
},
{
"cell_type": "code",
- "execution_count": 41,
+ "execution_count": 35,
"id": "3d91d737",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "ename": "FileNotFoundError",
+ "evalue": "[Errno 2] No such file or directory: 'data/submission.csv'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m/var/folders/tk/mrjkyqms0651_r4m4qvb9xz00000gn/T/ipykernel_43658/2451894762.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;31m#save as csv\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mfinal\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m'PassengerId'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mtitanic_sub\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'PassengerId'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'Survived'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0msubmission\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mfinal\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'data/submission.csv'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36mto_csv\u001b[0;34m(self, path_or_buf, sep, na_rep, float_format, columns, header, index, index_label, mode, encoding, compression, quoting, quotechar, line_terminator, chunksize, date_format, doublequote, escapechar, decimal, errors, storage_options)\u001b[0m\n\u001b[1;32m 3464\u001b[0m )\n\u001b[1;32m 3465\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3466\u001b[0;31m return DataFrameRenderer(formatter).to_csv(\n\u001b[0m\u001b[1;32m 3467\u001b[0m \u001b[0mpath_or_buf\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3468\u001b[0m \u001b[0mline_terminator\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mline_terminator\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/pandas/io/formats/format.py\u001b[0m in \u001b[0;36mto_csv\u001b[0;34m(self, path_or_buf, encoding, sep, columns, index_label, mode, compression, quoting, quotechar, line_terminator, chunksize, date_format, doublequote, escapechar, errors, storage_options)\u001b[0m\n\u001b[1;32m 1103\u001b[0m \u001b[0mformatter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfmt\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1104\u001b[0m )\n\u001b[0;32m-> 1105\u001b[0;31m \u001b[0mcsv_formatter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1106\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1107\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcreated_buffer\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/pandas/io/formats/csvs.py\u001b[0m in \u001b[0;36msave\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 235\u001b[0m \"\"\"\n\u001b[1;32m 236\u001b[0m \u001b[0;31m# apply compression and byte/text conversion\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 237\u001b[0;31m with get_handle(\n\u001b[0m\u001b[1;32m 238\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 239\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m~/opt/anaconda3/lib/python3.8/site-packages/pandas/io/common.py\u001b[0m in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m 700\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoding\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;34m\"b\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 701\u001b[0m \u001b[0;31m# Encoding\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 702\u001b[0;31m handle = open(\n\u001b[0m\u001b[1;32m 703\u001b[0m \u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 704\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'data/submission.csv'"
+ ]
+ }
+ ],
"source": [
"#create a data frame with passenger id and what class they belong to (if they survived or not)\n",
"#save as csv\n",
@@ -1047,21 +1037,10 @@
},
{
"cell_type": "code",
- "execution_count": 42,
+ "execution_count": null,
"id": "240feb73",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(418, 2)"
- ]
- },
- "execution_count": 42,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"final.shape"
]
@@ -1093,7 +1072,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.12"
+ "version": "3.8.2"
}
},
"nbformat": 4,
--
GitLab