Skip to content

Instantly share code, notes, and snippets.

@mirrornerror

mirrornerror/Titanic-Copy3.ipynb

Created November 1, 2018 10:48
Show Gist options
  • Save mirrornerror/2d6080a142c3d8536944ac107709192d to your computer and use it in GitHub Desktop.
Save mirrornerror/2d6080a142c3d8536944ac107709192d to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Titanic-Copy3.ipynb
{
"cells": [
{
"metadata": {},
"cell_type": "markdown",
"source": "# Kaggle: Titanic: Machine Learning from Disaster \nhttps://www.kaggle.com/c/titanic"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\n# random seed\nimport tensorflow as tf\nimport random as rn\nimport os\nos.environ['PYTHONHASHSEED'] = '0'\nrandom_n = 123\nnp.random.seed(random_n)\nrn.seed(random_n)\nsession_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)\nfrom keras import backend as K\ntf.set_random_seed(random_n)\nsess = tf.Session(graph=tf.get_default_graph(), config=session_conf)\nK.set_session(sess)\n\ntrain = pd.read_csv('train.csv', index_col=0)\ntest = pd.read_csv('test.csv', index_col=0)",
"execution_count": 51,
"outputs": []
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "train.head()",
"execution_count": 52,
"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>Survived</th>\n <th>Pclass</th>\n <th>Name</th>\n <th>Sex</th>\n <th>Age</th>\n <th>SibSp</th>\n <th>Parch</th>\n <th>Ticket</th>\n <th>Fare</th>\n <th>Cabin</th>\n <th>Embarked</th>\n </tr>\n <tr>\n <th>PassengerId</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 <th>1</th>\n <td>0</td>\n <td>3</td>\n <td>Braund, Mr. Owen Harris</td>\n <td>male</td>\n <td>22.0</td>\n <td>1</td>\n <td>0</td>\n <td>A/5 21171</td>\n <td>7.2500</td>\n <td>NaN</td>\n <td>S</td>\n </tr>\n <tr>\n <th>2</th>\n <td>1</td>\n <td>1</td>\n <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n <td>female</td>\n <td>38.0</td>\n <td>1</td>\n <td>0</td>\n <td>PC 17599</td>\n <td>71.2833</td>\n <td>C85</td>\n <td>C</td>\n </tr>\n <tr>\n <th>3</th>\n <td>1</td>\n <td>3</td>\n <td>Heikkinen, Miss. Laina</td>\n <td>female</td>\n <td>26.0</td>\n <td>0</td>\n <td>0</td>\n <td>STON/O2. 3101282</td>\n <td>7.9250</td>\n <td>NaN</td>\n <td>S</td>\n </tr>\n <tr>\n <th>4</th>\n <td>1</td>\n <td>1</td>\n <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n <td>female</td>\n <td>35.0</td>\n <td>1</td>\n <td>0</td>\n <td>113803</td>\n <td>53.1000</td>\n <td>C123</td>\n <td>S</td>\n </tr>\n <tr>\n <th>5</th>\n <td>0</td>\n <td>3</td>\n <td>Allen, Mr. William Henry</td>\n <td>male</td>\n <td>35.0</td>\n <td>0</td>\n <td>0</td>\n <td>373450</td>\n <td>8.0500</td>\n <td>NaN</td>\n <td>S</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " Survived Pclass \\\nPassengerId \n1 0 3 \n2 1 1 \n3 1 3 \n4 1 1 \n5 0 3 \n\n Name Sex Age \\\nPassengerId \n1 Braund, Mr. Owen Harris male 22.0 \n2 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 \n3 Heikkinen, Miss. Laina female 26.0 \n4 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 \n5 Allen, Mr. William Henry male 35.0 \n\n SibSp Parch Ticket Fare Cabin Embarked \nPassengerId \n1 1 0 A/5 21171 7.2500 NaN S \n2 1 0 PC 17599 71.2833 C85 C \n3 0 0 STON/O2. 3101282 7.9250 NaN S \n4 1 0 113803 53.1000 C123 S \n5 0 0 373450 8.0500 NaN S "
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Drop Survived and Ticket, then combine train with test "
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "train_tmp = train.drop(['Survived', 'Ticket'], axis=1)\ntest_tmp = test.drop(['Ticket'], axis=1)\ndf = pd.concat([train_tmp, test_tmp])\ndf.info()",
"execution_count": 53,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "<class 'pandas.core.frame.DataFrame'>\nInt64Index: 1309 entries, 1 to 1309\nData columns (total 9 columns):\nPclass 1309 non-null int64\nName 1309 non-null object\nSex 1309 non-null object\nAge 1046 non-null float64\nSibSp 1309 non-null int64\nParch 1309 non-null int64\nFare 1308 non-null float64\nCabin 295 non-null object\nEmbarked 1307 non-null object\ndtypes: float64(2), int64(3), object(4)\nmemory usage: 102.3+ KB\n"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Name --> Title --> Number"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# Name to Title\ndf = df.assign(Title=df.Name.str.extract(' ([A-Za-z]+)\\..', expand=True))\ntitle_list = df.Title.unique()\nprint(title_list)",
"execution_count": 54,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "['Mr' 'Mrs' 'Miss' 'Master' 'Don' 'Rev' 'Dr' 'Mme' 'Ms' 'Major' 'Lady'\n 'Sir' 'Mlle' 'Col' 'Capt' 'Countess' 'Jonkheer' 'Dona']\n"
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# Title to Number(0-17)\ndf.Title = df.Title.replace(df.Title.unique(), np.arange(len(df.Title.unique())))\n\n# Drop Name column\ndf = df.drop(['Name'], axis=1)\ndf.head()",
"execution_count": 55,
"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>Pclass</th>\n <th>Sex</th>\n <th>Age</th>\n <th>SibSp</th>\n <th>Parch</th>\n <th>Fare</th>\n <th>Cabin</th>\n <th>Embarked</th>\n <th>Title</th>\n </tr>\n <tr>\n <th>PassengerId</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 <th>1</th>\n <td>3</td>\n <td>male</td>\n <td>22.0</td>\n <td>1</td>\n <td>0</td>\n <td>7.2500</td>\n <td>NaN</td>\n <td>S</td>\n <td>0</td>\n </tr>\n <tr>\n <th>2</th>\n <td>1</td>\n <td>female</td>\n <td>38.0</td>\n <td>1</td>\n <td>0</td>\n <td>71.2833</td>\n <td>C85</td>\n <td>C</td>\n <td>1</td>\n </tr>\n <tr>\n <th>3</th>\n <td>3</td>\n <td>female</td>\n <td>26.0</td>\n <td>0</td>\n <td>0</td>\n <td>7.9250</td>\n <td>NaN</td>\n <td>S</td>\n <td>2</td>\n </tr>\n <tr>\n <th>4</th>\n <td>1</td>\n <td>female</td>\n <td>35.0</td>\n <td>1</td>\n <td>0</td>\n <td>53.1000</td>\n <td>C123</td>\n <td>S</td>\n <td>1</td>\n </tr>\n <tr>\n <th>5</th>\n <td>3</td>\n <td>male</td>\n <td>35.0</td>\n <td>0</td>\n <td>0</td>\n <td>8.0500</td>\n <td>NaN</td>\n <td>S</td>\n <td>0</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " Pclass Sex Age SibSp Parch Fare Cabin Embarked Title\nPassengerId \n1 3 male 22.0 1 0 7.2500 NaN S 0\n2 1 female 38.0 1 0 71.2833 C85 C 1\n3 3 female 26.0 0 0 7.9250 NaN S 2\n4 1 female 35.0 1 0 53.1000 C123 S 1\n5 3 male 35.0 0 0 8.0500 NaN S 0"
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Sex --> male:0, female:1"
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "df.Sex = df.Sex.replace({'male': 0, 'female': 1})",
"execution_count": 56,
"outputs": []
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Cabin --> Number: nan:0, C:1, E:2, G:3, D:4, A:5, B:6, F:7, T:8"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "df = df.assign(Cabin=df.Cabin.str[0])\ncabin_list = df.Cabin.unique()\n\ndf.Cabin = df.Cabin.replace(df.Cabin.str[0].unique(), np.arange(len(df.Cabin.str[0].unique())))\n\nprint(cabin_list)\nprint(df.Cabin.unique())",
"execution_count": 57,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "[nan 'C' 'E' 'G' 'D' 'A' 'B' 'F' 'T']\n[0 1 2 3 4 5 6 7 8]\n"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Embarked --> S:0, C:1, Q:2, nan"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "df.Embarked.unique()",
"execution_count": 58,
"outputs": [
{
"data": {
"text/plain": "array(['S', 'C', 'Q', nan], dtype=object)"
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "df.Embarked = df.Embarked.replace({'S':0, 'C':1, 'Q':2})",
"execution_count": 59,
"outputs": []
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## zscore or normalization: \n* Age: including NaN\n* Fare: including NaN \n \nZ = (x - x.mean) / x.std \nN = (x - x.min)/(x.max - x.min) \n \nsklearn.preprocessing.MinMaxScaler causes error with Null data."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# Normalize Function\ndef normalize(df_col):\n df_col = (df_col - df_col.min()) / (df_col.max() - df_col.min())\n return df_col",
"execution_count": 60,
"outputs": []
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# Standardization(zscore)\ndef zscore(df_col):\n df_col = (df_col - df_col.mean()) / df_col.std()\n return df_col",
"execution_count": 61,
"outputs": []
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "df.Age = zscore(df.Age)\ndf.Fare = zscore(df.Fare)\n# df.SibSp = zscore(df.SibSp)\n# df.Parch = zscore(df.Parch)\n# df.Title = zscore(df.Title)\n\n# df.Age = normalize(df.Age)\n# df.Fare = normalize(df.Fare)\n\n# for col in df.columns:\n# df[col] = zscore(df[col])\n\ndf.describe()",
"execution_count": 62,
"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>Pclass</th>\n <th>Sex</th>\n <th>Age</th>\n <th>SibSp</th>\n <th>Parch</th>\n <th>Fare</th>\n <th>Cabin</th>\n <th>Embarked</th>\n <th>Title</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>count</th>\n <td>1309.000000</td>\n <td>1309.000000</td>\n <td>1046.000000</td>\n <td>1309.000000</td>\n <td>1309.000000</td>\n <td>1308.000000</td>\n <td>1309.000000</td>\n <td>1307.000000</td>\n <td>1309.000000</td>\n </tr>\n <tr>\n <th>mean</th>\n <td>2.294882</td>\n <td>0.355997</td>\n <td>0.372180</td>\n <td>0.498854</td>\n <td>0.385027</td>\n <td>0.064988</td>\n <td>0.786860</td>\n <td>0.394797</td>\n <td>0.910619</td>\n </tr>\n <tr>\n <th>std</th>\n <td>0.837836</td>\n <td>0.478997</td>\n <td>0.180552</td>\n <td>1.041658</td>\n <td>0.865560</td>\n <td>0.101026</td>\n <td>1.794388</td>\n <td>0.653817</td>\n <td>1.680647</td>\n </tr>\n <tr>\n <th>min</th>\n <td>1.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n </tr>\n <tr>\n <th>25%</th>\n <td>2.000000</td>\n <td>0.000000</td>\n <td>0.260929</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.015412</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n </tr>\n <tr>\n <th>50%</th>\n <td>3.000000</td>\n <td>0.000000</td>\n <td>0.348616</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.028213</td>\n <td>0.000000</td>\n <td>0.000000</td>\n <td>0.000000</td>\n </tr>\n <tr>\n <th>75%</th>\n <td>3.000000</td>\n <td>1.000000</td>\n <td>0.486409</td>\n <td>1.000000</td>\n <td>0.000000</td>\n <td>0.061045</td>\n <td>0.000000</td>\n <td>1.000000</td>\n <td>2.000000</td>\n </tr>\n <tr>\n <th>max</th>\n <td>3.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>8.000000</td>\n <td>9.000000</td>\n <td>1.000000</td>\n <td>8.000000</td>\n <td>2.000000</td>\n <td>17.000000</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " Pclass Sex Age SibSp Parch \\\ncount 1309.000000 1309.000000 1046.000000 1309.000000 1309.000000 \nmean 2.294882 0.355997 0.372180 0.498854 0.385027 \nstd 0.837836 0.478997 0.180552 1.041658 0.865560 \nmin 1.000000 0.000000 0.000000 0.000000 0.000000 \n25% 2.000000 0.000000 0.260929 0.000000 0.000000 \n50% 3.000000 0.000000 0.348616 0.000000 0.000000 \n75% 3.000000 1.000000 0.486409 1.000000 0.000000 \nmax 3.000000 1.000000 1.000000 8.000000 9.000000 \n\n Fare Cabin Embarked Title \ncount 1308.000000 1309.000000 1307.000000 1309.000000 \nmean 0.064988 0.786860 0.394797 0.910619 \nstd 0.101026 1.794388 0.653817 1.680647 \nmin 0.000000 0.000000 0.000000 0.000000 \n25% 0.015412 0.000000 0.000000 0.000000 \n50% 0.028213 0.000000 0.000000 0.000000 \n75% 0.061045 0.000000 1.000000 2.000000 \nmax 1.000000 8.000000 2.000000 17.000000 "
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Separate Notnull data from Null data\n\nMake a Copy of df: df0 = df.copy() \n* Age\n* Embarked\n* Fare\n"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# drop Cabin\n#df = df.drop(['Cabin'], axis=1)\n\ndf0 = df.copy()\ndf0.info()",
"execution_count": 63,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "<class 'pandas.core.frame.DataFrame'>\nInt64Index: 1309 entries, 1 to 1309\nData columns (total 9 columns):\nPclass 1309 non-null int64\nSex 1309 non-null int64\nAge 1046 non-null float64\nSibSp 1309 non-null int64\nParch 1309 non-null int64\nFare 1308 non-null float64\nCabin 1309 non-null int64\nEmbarked 1307 non-null float64\nTitle 1309 non-null int64\ndtypes: float64(3), int64(6)\nmemory usage: 102.3 KB\n"
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "Age_null = df[df.Age.isnull()]\ndf = df[df.Age.notnull()]\n\nEmbarked_null = df[df.Embarked.isnull()]\ndf = df[df.Embarked.notnull()]\n\nFare_null = df[df.Fare.isnull()]\ndf = df[df.Fare.notnull()]",
"execution_count": 64,
"outputs": []
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Notnull Data: df.shape = (1043, 9)"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "print(df.shape)\ndf.info()",
"execution_count": 65,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "(1043, 9)\n<class 'pandas.core.frame.DataFrame'>\nInt64Index: 1043 entries, 1 to 1307\nData columns (total 9 columns):\nPclass 1043 non-null int64\nSex 1043 non-null int64\nAge 1043 non-null float64\nSibSp 1043 non-null int64\nParch 1043 non-null int64\nFare 1043 non-null float64\nCabin 1043 non-null int64\nEmbarked 1043 non-null float64\nTitle 1043 non-null int64\ndtypes: float64(3), int64(6)\nmemory usage: 81.5 KB\n"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Model to fill NaN in Fare, Embarked, Age"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "from keras.models import Sequential\nfrom keras.layers import Flatten, Dense, Dropout, BatchNormalization\n\n# model for Fare, Embarked, Age\ndef fill_data(col):\n n_cols = len(df.columns) - 1\n num = len(df[col].unique())\n \n model = Sequential()\n model.add(Dense(64, activation='relu', input_shape=(n_cols,)))\n model.add(Dropout(0.5))\n \n if col == 'Embarked':\n model.add(Dense(num, activation='softmax'))\n model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['acc'])\n else: # 'Fare', 'Age'\n model.add(Dense(1, activation='linear'))\n model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])\n \n data = df.drop([col], axis=1)\n epochs = 100\n hist = model.fit(data, df[col], epochs=epochs, batch_size=32)\n\n null_data = df0[df0[col].isnull()]\n null_data = null_data.drop([col], axis=1)\n pred = model.predict(null_data)\n \n if col == 'Embarked':\n pred = pred.argmax(axis=1)\n \n plt.plot(hist.history['acc'], 'b-', label='acc' )\n plt.plot(hist.history['loss'], 'r-', label='loss' )\n plt.xlabel('epochs')\n plt.legend()\n plt.show()\n \n pred = pred.reshape(-1, )\n \n idx = df0[df0[col].isnull()].index.values\n\n for n, i in enumerate(idx):\n df0.loc[i, col] = pred[n]",
"execution_count": 66,
"outputs": []
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "fill_data('Embarked') # id:62,830",
"execution_count": 67,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "Epoch 1/100\n1043/1043 [==============================] - 0s 294us/step - loss: 0.8236 - acc: 0.6999\nEpoch 2/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.7232 - acc: 0.7459\nEpoch 3/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.7199 - acc: 0.7277\nEpoch 4/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6917 - acc: 0.7402\nEpoch 5/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.6938 - acc: 0.7373\nEpoch 6/100\n1043/1043 [==============================] - 0s 70us/step - loss: 0.6806 - acc: 0.7440\nEpoch 7/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6797 - acc: 0.7536\nEpoch 8/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.6721 - acc: 0.7507\nEpoch 9/100\n1043/1043 [==============================] - 0s 71us/step - loss: 0.6662 - acc: 0.7459\nEpoch 10/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.6522 - acc: 0.7517\nEpoch 11/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.6574 - acc: 0.7411\nEpoch 12/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.6362 - acc: 0.7498\nEpoch 13/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6571 - acc: 0.7526\nEpoch 14/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6585 - acc: 0.7315\nEpoch 15/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6453 - acc: 0.7469\nEpoch 16/100\n1043/1043 [==============================] - 0s 69us/step - loss: 0.6298 - acc: 0.7565\nEpoch 17/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6305 - acc: 0.7574\nEpoch 18/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6366 - acc: 0.7536\nEpoch 19/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6275 - acc: 0.7546\nEpoch 20/100\n1043/1043 [==============================] - 0s 67us/step - loss: 0.6293 - acc: 0.7593\nEpoch 21/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6277 - acc: 0.7526\nEpoch 22/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6327 - acc: 0.7488\nEpoch 23/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.6387 - acc: 0.7507\nEpoch 24/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.6372 - acc: 0.7421\nEpoch 25/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.6302 - acc: 0.7555\nEpoch 26/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6328 - acc: 0.7507\nEpoch 27/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6266 - acc: 0.7478\nEpoch 28/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6448 - acc: 0.7507\nEpoch 29/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6118 - acc: 0.7517\nEpoch 30/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6226 - acc: 0.7526\nEpoch 31/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.6207 - acc: 0.7536\nEpoch 32/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6360 - acc: 0.7488\nEpoch 33/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.6279 - acc: 0.7498\nEpoch 34/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.6178 - acc: 0.7565\nEpoch 35/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6097 - acc: 0.7555\nEpoch 36/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.6193 - acc: 0.7469\nEpoch 37/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.6195 - acc: 0.7565\nEpoch 38/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6218 - acc: 0.7526\nEpoch 39/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6116 - acc: 0.7565\nEpoch 40/100\n1043/1043 [==============================] - 0s 57us/step - loss: 0.6143 - acc: 0.7670\nEpoch 41/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6103 - acc: 0.7574\nEpoch 42/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6211 - acc: 0.7440\nEpoch 43/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.6111 - acc: 0.7546\nEpoch 44/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.6033 - acc: 0.7526\nEpoch 45/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.6152 - acc: 0.7517\nEpoch 46/100\n1043/1043 [==============================] - 0s 69us/step - loss: 0.6111 - acc: 0.7555\nEpoch 47/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6191 - acc: 0.7555\nEpoch 48/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.6143 - acc: 0.7593\nEpoch 49/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6192 - acc: 0.7517\nEpoch 50/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6107 - acc: 0.7517\nEpoch 51/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.6031 - acc: 0.7641\nEpoch 52/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.6016 - acc: 0.7574\nEpoch 53/100\n1043/1043 [==============================] - ETA: 0s - loss: 0.6441 - acc: 0.757 - 0s 60us/step - loss: 0.6166 - acc: 0.7699\nEpoch 54/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6087 - acc: 0.7641\nEpoch 55/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.6011 - acc: 0.7622\nEpoch 56/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6070 - acc: 0.7488\nEpoch 57/100\n1043/1043 [==============================] - 0s 68us/step - loss: 0.6002 - acc: 0.7546\nEpoch 58/100\n1043/1043 [==============================] - 0s 68us/step - loss: 0.6088 - acc: 0.7574\nEpoch 59/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6132 - acc: 0.7450\nEpoch 60/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.5994 - acc: 0.7584\nEpoch 61/100\n1043/1043 [==============================] - 0s 71us/step - loss: 0.5947 - acc: 0.7593\nEpoch 62/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.6034 - acc: 0.7632\nEpoch 63/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.5933 - acc: 0.7574\nEpoch 64/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.6092 - acc: 0.7593\nEpoch 65/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6114 - acc: 0.7526\nEpoch 66/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.5984 - acc: 0.7641\nEpoch 67/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.5957 - acc: 0.7689\nEpoch 68/100\n1043/1043 [==============================] - 0s 67us/step - loss: 0.6015 - acc: 0.7603\nEpoch 69/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.5957 - acc: 0.7546\nEpoch 70/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.5902 - acc: 0.7680\nEpoch 71/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.6064 - acc: 0.7555\nEpoch 72/100\n1043/1043 [==============================] - 0s 69us/step - loss: 0.6073 - acc: 0.7574\nEpoch 73/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6039 - acc: 0.7641\nEpoch 74/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.6113 - acc: 0.7641\nEpoch 75/100\n1043/1043 [==============================] - 0s 67us/step - loss: 0.6014 - acc: 0.7661\nEpoch 76/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.5936 - acc: 0.7603\nEpoch 77/100\n1043/1043 [==============================] - 0s 67us/step - loss: 0.5959 - acc: 0.7613\nEpoch 78/100\n1043/1043 [==============================] - 0s 74us/step - loss: 0.6087 - acc: 0.7584\nEpoch 79/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.6004 - acc: 0.7641: 0s - loss: 0.5813 - acc: 0.769\nEpoch 80/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.6010 - acc: 0.7603\nEpoch 81/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.5952 - acc: 0.7613\nEpoch 82/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.5870 - acc: 0.7574\nEpoch 83/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.5938 - acc: 0.7546\nEpoch 84/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.5944 - acc: 0.7593\nEpoch 85/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.5938 - acc: 0.7613\nEpoch 86/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.5914 - acc: 0.7651\nEpoch 87/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.6002 - acc: 0.7536\nEpoch 88/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.5964 - acc: 0.7651\nEpoch 89/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.5958 - acc: 0.7622\nEpoch 90/100\n1043/1043 [==============================] - 0s 69us/step - loss: 0.5923 - acc: 0.7680\nEpoch 91/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.5919 - acc: 0.7613\nEpoch 92/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.5898 - acc: 0.7632\nEpoch 93/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.5836 - acc: 0.7661\nEpoch 94/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.5990 - acc: 0.7680\nEpoch 95/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.5962 - acc: 0.7632\nEpoch 96/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.5949 - acc: 0.7622\nEpoch 97/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.5989 - acc: 0.7670\nEpoch 98/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.5867 - acc: 0.7613\nEpoch 99/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.5928 - acc: 0.7622\nEpoch 100/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.5914 - acc: 0.7709\n"
},
{
"data": {
"image/png": "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\n",
"text/plain": "<matplotlib.figure.Figure at 0x7f910e0bde10>"
},
"metadata": {},
"output_type": "display_data"
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "fill_data('Fare') # id:1044",
"execution_count": 68,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "Epoch 1/100\n1043/1043 [==============================] - 0s 269us/step - loss: 0.4049 - mean_absolute_error: 0.4225\nEpoch 2/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.2513 - mean_absolute_error: 0.3314\nEpoch 3/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.1964 - mean_absolute_error: 0.2904\nEpoch 4/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.1269 - mean_absolute_error: 0.2285\nEpoch 5/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0923 - mean_absolute_error: 0.1945\nEpoch 6/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0721 - mean_absolute_error: 0.1554\nEpoch 7/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0405 - mean_absolute_error: 0.1232\nEpoch 8/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0466 - mean_absolute_error: 0.1148\nEpoch 9/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0432 - mean_absolute_error: 0.0979\nEpoch 10/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0314 - mean_absolute_error: 0.0841\nEpoch 11/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0277 - mean_absolute_error: 0.0788\nEpoch 12/100\n1043/1043 [==============================] - 0s 70us/step - loss: 0.0184 - mean_absolute_error: 0.0679\nEpoch 13/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0175 - mean_absolute_error: 0.0620\nEpoch 14/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.0206 - mean_absolute_error: 0.0624\nEpoch 15/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0186 - mean_absolute_error: 0.0593\nEpoch 16/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0210 - mean_absolute_error: 0.0597\nEpoch 17/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0164 - mean_absolute_error: 0.0569\nEpoch 18/100\n1043/1043 [==============================] - ETA: 0s - loss: 0.0172 - mean_absolute_error: 0.054 - 0s 65us/step - loss: 0.0176 - mean_absolute_error: 0.0561\nEpoch 19/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0129 - mean_absolute_error: 0.0535\nEpoch 20/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0099 - mean_absolute_error: 0.0489\nEpoch 21/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0098 - mean_absolute_error: 0.0497\nEpoch 22/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0104 - mean_absolute_error: 0.0502\nEpoch 23/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0108 - mean_absolute_error: 0.0493\nEpoch 24/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0090 - mean_absolute_error: 0.0498\nEpoch 25/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0099 - mean_absolute_error: 0.0500\nEpoch 26/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0097 - mean_absolute_error: 0.0500\nEpoch 27/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.0089 - mean_absolute_error: 0.0478\nEpoch 28/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0091 - mean_absolute_error: 0.0468\nEpoch 29/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0106 - mean_absolute_error: 0.0486\nEpoch 30/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0077 - mean_absolute_error: 0.0457\nEpoch 31/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0077 - mean_absolute_error: 0.0463\nEpoch 32/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.0086 - mean_absolute_error: 0.0468\nEpoch 33/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.0074 - mean_absolute_error: 0.0448\nEpoch 34/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0093 - mean_absolute_error: 0.0469\nEpoch 35/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0078 - mean_absolute_error: 0.0457\nEpoch 36/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.0073 - mean_absolute_error: 0.0454\nEpoch 37/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0073 - mean_absolute_error: 0.0440\nEpoch 38/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0069 - mean_absolute_error: 0.0448\nEpoch 39/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.0081 - mean_absolute_error: 0.0465\nEpoch 40/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0072 - mean_absolute_error: 0.0444\nEpoch 41/100\n1043/1043 [==============================] - 0s 67us/step - loss: 0.0073 - mean_absolute_error: 0.0445\nEpoch 42/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0070 - mean_absolute_error: 0.0437\nEpoch 43/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0075 - mean_absolute_error: 0.0443\nEpoch 44/100\n1043/1043 [==============================] - 0s 68us/step - loss: 0.0073 - mean_absolute_error: 0.0450\nEpoch 45/100\n1043/1043 [==============================] - 0s 89us/step - loss: 0.0069 - mean_absolute_error: 0.0435\nEpoch 46/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.0073 - mean_absolute_error: 0.0437\nEpoch 47/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0065 - mean_absolute_error: 0.0428\nEpoch 48/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0065 - mean_absolute_error: 0.0397\nEpoch 49/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0066 - mean_absolute_error: 0.0421\nEpoch 50/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0063 - mean_absolute_error: 0.0416\nEpoch 51/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0066 - mean_absolute_error: 0.0418\nEpoch 52/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0065 - mean_absolute_error: 0.0424\nEpoch 53/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0068 - mean_absolute_error: 0.0419\nEpoch 54/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0067 - mean_absolute_error: 0.0425\nEpoch 55/100\n1043/1043 [==============================] - 0s 74us/step - loss: 0.0065 - mean_absolute_error: 0.0405\nEpoch 56/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0065 - mean_absolute_error: 0.0410\nEpoch 57/100\n1043/1043 [==============================] - 0s 75us/step - loss: 0.0069 - mean_absolute_error: 0.0423\nEpoch 58/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0067 - mean_absolute_error: 0.0415\nEpoch 59/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0064 - mean_absolute_error: 0.0412\nEpoch 60/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0067 - mean_absolute_error: 0.0421\nEpoch 61/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0065 - mean_absolute_error: 0.0407\nEpoch 62/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0065 - mean_absolute_error: 0.0410\nEpoch 63/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0065 - mean_absolute_error: 0.0410\nEpoch 64/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0068 - mean_absolute_error: 0.0429\nEpoch 65/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0063 - mean_absolute_error: 0.0407\nEpoch 66/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0064 - mean_absolute_error: 0.0403\nEpoch 67/100\n1043/1043 [==============================] - 0s 57us/step - loss: 0.0061 - mean_absolute_error: 0.0396\nEpoch 68/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0060 - mean_absolute_error: 0.0404\nEpoch 69/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0065 - mean_absolute_error: 0.0408\nEpoch 70/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0066 - mean_absolute_error: 0.0406\nEpoch 71/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0062 - mean_absolute_error: 0.0401\nEpoch 72/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0060 - mean_absolute_error: 0.0397\nEpoch 73/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0063 - mean_absolute_error: 0.0396\nEpoch 74/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0062 - mean_absolute_error: 0.0396\nEpoch 75/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0057 - mean_absolute_error: 0.0389\nEpoch 76/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0060 - mean_absolute_error: 0.0399\nEpoch 77/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0061 - mean_absolute_error: 0.0384\nEpoch 78/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0064 - mean_absolute_error: 0.0406\nEpoch 79/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0059 - mean_absolute_error: 0.0389\nEpoch 80/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0062 - mean_absolute_error: 0.0403\nEpoch 81/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0060 - mean_absolute_error: 0.0387\nEpoch 82/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0064 - mean_absolute_error: 0.0392\nEpoch 83/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0060 - mean_absolute_error: 0.0386\nEpoch 84/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0067 - mean_absolute_error: 0.0412\nEpoch 85/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0058 - mean_absolute_error: 0.0379\nEpoch 86/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0061 - mean_absolute_error: 0.0391\nEpoch 87/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0062 - mean_absolute_error: 0.0398\nEpoch 88/100\n1043/1043 [==============================] - 0s 69us/step - loss: 0.0056 - mean_absolute_error: 0.0379\nEpoch 89/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0065 - mean_absolute_error: 0.0396\nEpoch 90/100\n1043/1043 [==============================] - 0s 55us/step - loss: 0.0058 - mean_absolute_error: 0.0391\nEpoch 91/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0058 - mean_absolute_error: 0.0392\nEpoch 92/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0055 - mean_absolute_error: 0.0383\nEpoch 93/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0059 - mean_absolute_error: 0.0378\nEpoch 94/100\n1043/1043 [==============================] - 0s 57us/step - loss: 0.0064 - mean_absolute_error: 0.0399\nEpoch 95/100\n1043/1043 [==============================] - 0s 55us/step - loss: 0.0059 - mean_absolute_error: 0.0394\nEpoch 96/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0059 - mean_absolute_error: 0.0381\nEpoch 97/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0057 - mean_absolute_error: 0.0389\nEpoch 98/100\n1043/1043 [==============================] - 0s 55us/step - loss: 0.0061 - mean_absolute_error: 0.0379\nEpoch 99/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0055 - mean_absolute_error: 0.0377\nEpoch 100/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0057 - mean_absolute_error: 0.0382\n"
}
]
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "fill_data('Age') # id: 6,18,20,27,29,30",
"execution_count": 69,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "Epoch 1/100\n1043/1043 [==============================] - 0s 281us/step - loss: 0.5160 - mean_absolute_error: 0.5382\nEpoch 2/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.3610 - mean_absolute_error: 0.4385\nEpoch 3/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.2563 - mean_absolute_error: 0.3521\nEpoch 4/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.2049 - mean_absolute_error: 0.3167\nEpoch 5/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.1310 - mean_absolute_error: 0.2734\nEpoch 6/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.1035 - mean_absolute_error: 0.2365\nEpoch 7/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0856 - mean_absolute_error: 0.2075\nEpoch 8/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0756 - mean_absolute_error: 0.1910\nEpoch 9/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0705 - mean_absolute_error: 0.1780\nEpoch 10/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0484 - mean_absolute_error: 0.1637\nEpoch 11/100\n1043/1043 [==============================] - 0s 69us/step - loss: 0.0503 - mean_absolute_error: 0.1579\nEpoch 12/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0423 - mean_absolute_error: 0.1478\nEpoch 13/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0386 - mean_absolute_error: 0.1415\nEpoch 14/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0383 - mean_absolute_error: 0.1383\nEpoch 15/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0333 - mean_absolute_error: 0.1365\nEpoch 16/100\n1043/1043 [==============================] - 0s 57us/step - loss: 0.0332 - mean_absolute_error: 0.1329\nEpoch 17/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0287 - mean_absolute_error: 0.1282\nEpoch 18/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0264 - mean_absolute_error: 0.1234\nEpoch 19/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0266 - mean_absolute_error: 0.1238\nEpoch 20/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0282 - mean_absolute_error: 0.1247\nEpoch 21/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0258 - mean_absolute_error: 0.1213\nEpoch 22/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0271 - mean_absolute_error: 0.1227\nEpoch 23/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0250 - mean_absolute_error: 0.1219\nEpoch 24/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0256 - mean_absolute_error: 0.1239\nEpoch 25/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0244 - mean_absolute_error: 0.1211\nEpoch 26/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0264 - mean_absolute_error: 0.1227\nEpoch 27/100\n1043/1043 [==============================] - 0s 70us/step - loss: 0.0247 - mean_absolute_error: 0.1207\nEpoch 28/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0231 - mean_absolute_error: 0.1163\nEpoch 29/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0254 - mean_absolute_error: 0.1200\nEpoch 30/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0248 - mean_absolute_error: 0.1196\nEpoch 31/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0255 - mean_absolute_error: 0.1190\nEpoch 32/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0229 - mean_absolute_error: 0.1183\nEpoch 33/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0221 - mean_absolute_error: 0.1166\nEpoch 34/100\n1043/1043 [==============================] - 0s 57us/step - loss: 0.0241 - mean_absolute_error: 0.1181\nEpoch 35/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0237 - mean_absolute_error: 0.1176\nEpoch 36/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0229 - mean_absolute_error: 0.1169\nEpoch 37/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0230 - mean_absolute_error: 0.1182\nEpoch 38/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0236 - mean_absolute_error: 0.1181\nEpoch 39/100\n1043/1043 [==============================] - 0s 69us/step - loss: 0.0229 - mean_absolute_error: 0.1171\nEpoch 40/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0217 - mean_absolute_error: 0.1140\nEpoch 41/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0217 - mean_absolute_error: 0.1155\nEpoch 42/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0217 - mean_absolute_error: 0.1146\nEpoch 43/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0222 - mean_absolute_error: 0.1163\nEpoch 44/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0226 - mean_absolute_error: 0.1178\nEpoch 45/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0216 - mean_absolute_error: 0.1146\nEpoch 46/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0224 - mean_absolute_error: 0.1162\nEpoch 47/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0226 - mean_absolute_error: 0.1171\nEpoch 48/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.0212 - mean_absolute_error: 0.1136\nEpoch 49/100\n1043/1043 [==============================] - 0s 67us/step - loss: 0.0219 - mean_absolute_error: 0.1144\nEpoch 50/100\n1043/1043 [==============================] - 0s 68us/step - loss: 0.0223 - mean_absolute_error: 0.1154\nEpoch 51/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.0226 - mean_absolute_error: 0.1177\nEpoch 52/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0226 - mean_absolute_error: 0.1169\nEpoch 53/100\n1043/1043 [==============================] - 0s 68us/step - loss: 0.0217 - mean_absolute_error: 0.1143\nEpoch 54/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0220 - mean_absolute_error: 0.1153\nEpoch 55/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.0214 - mean_absolute_error: 0.1142\nEpoch 56/100\n1043/1043 [==============================] - 0s 66us/step - loss: 0.0213 - mean_absolute_error: 0.1136\nEpoch 57/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0217 - mean_absolute_error: 0.1125\nEpoch 58/100\n1043/1043 [==============================] - 0s 64us/step - loss: 0.0214 - mean_absolute_error: 0.1129\nEpoch 59/100\n1043/1043 [==============================] - 0s 56us/step - loss: 0.0214 - mean_absolute_error: 0.1136\nEpoch 60/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0212 - mean_absolute_error: 0.1131\nEpoch 61/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0211 - mean_absolute_error: 0.1128\nEpoch 62/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0225 - mean_absolute_error: 0.1150\nEpoch 63/100\n1043/1043 [==============================] - 0s 77us/step - loss: 0.0219 - mean_absolute_error: 0.1151\nEpoch 64/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0216 - mean_absolute_error: 0.1141\nEpoch 65/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0213 - mean_absolute_error: 0.1141\nEpoch 66/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0209 - mean_absolute_error: 0.1138\nEpoch 67/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0221 - mean_absolute_error: 0.1149\nEpoch 68/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0216 - mean_absolute_error: 0.1139\nEpoch 69/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0221 - mean_absolute_error: 0.1151\nEpoch 70/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0213 - mean_absolute_error: 0.1125\nEpoch 71/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0212 - mean_absolute_error: 0.1145\nEpoch 72/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0215 - mean_absolute_error: 0.1140\nEpoch 73/100\n1043/1043 [==============================] - 0s 79us/step - loss: 0.0217 - mean_absolute_error: 0.1135\nEpoch 74/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0211 - mean_absolute_error: 0.1122\nEpoch 75/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0217 - mean_absolute_error: 0.1154\nEpoch 76/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0218 - mean_absolute_error: 0.1132\nEpoch 77/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0214 - mean_absolute_error: 0.1146\nEpoch 78/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0212 - mean_absolute_error: 0.1122\nEpoch 79/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0209 - mean_absolute_error: 0.1132\nEpoch 80/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0220 - mean_absolute_error: 0.1149\nEpoch 81/100\n1043/1043 [==============================] - 0s 57us/step - loss: 0.0210 - mean_absolute_error: 0.1135\nEpoch 82/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0205 - mean_absolute_error: 0.1123\nEpoch 83/100\n1043/1043 [==============================] - 0s 54us/step - loss: 0.0211 - mean_absolute_error: 0.1133\nEpoch 84/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0211 - mean_absolute_error: 0.1116\nEpoch 85/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0209 - mean_absolute_error: 0.1133\nEpoch 86/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0217 - mean_absolute_error: 0.1134\nEpoch 87/100\n1043/1043 [==============================] - 0s 62us/step - loss: 0.0215 - mean_absolute_error: 0.1138\nEpoch 88/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0212 - mean_absolute_error: 0.1136\nEpoch 89/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.0219 - mean_absolute_error: 0.1146\nEpoch 90/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0205 - mean_absolute_error: 0.1114\nEpoch 91/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0210 - mean_absolute_error: 0.1125\nEpoch 92/100\n1043/1043 [==============================] - 0s 59us/step - loss: 0.0210 - mean_absolute_error: 0.1125\nEpoch 93/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0220 - mean_absolute_error: 0.1146\nEpoch 94/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0203 - mean_absolute_error: 0.1106\nEpoch 95/100\n1043/1043 [==============================] - 0s 63us/step - loss: 0.0209 - mean_absolute_error: 0.1108\nEpoch 96/100\n1043/1043 [==============================] - 0s 61us/step - loss: 0.0222 - mean_absolute_error: 0.1145\nEpoch 97/100\n1043/1043 [==============================] - 0s 65us/step - loss: 0.0203 - mean_absolute_error: 0.1097\nEpoch 98/100\n1043/1043 [==============================] - 0s 58us/step - loss: 0.0219 - mean_absolute_error: 0.1138\nEpoch 99/100\n1043/1043 [==============================] - 0s 60us/step - loss: 0.0211 - mean_absolute_error: 0.1145\nEpoch 100/100\n1043/1043 [==============================] - 0s 57us/step - loss: 0.0208 - mean_absolute_error: 0.1130\n"
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# Drop Title\ndf0 = df0.drop(['Title'], axis=1)\n# df0.head()",
"execution_count": 70,
"outputs": []
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "train0 = df0[0:891].copy()\ntest0 = df0[891:].copy()",
"execution_count": 71,
"outputs": []
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Model to estimate Survived for submission"
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "df0_cols = len(df0.columns)\n\nmodel = Sequential()\nmodel.add(Dense(64, activation='relu', input_shape=(df0_cols,)))\n#model.add(BatchNormalization())\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(2, activation='softmax'))\nmodel.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['acc'])\n\nepochs = 100\nmf = model.fit(train0, train.Survived, epochs=epochs, batch_size=5)\n\npred = model.predict(test0)",
"execution_count": 72,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": "Epoch 1/100\n891/891 [==============================] - 1s 644us/step - loss: 0.7036 - acc: 0.5746\nEpoch 2/100\n891/891 [==============================] - 0s 390us/step - loss: 0.5448 - acc: 0.7284\nEpoch 3/100\n891/891 [==============================] - 0s 376us/step - loss: 0.5220 - acc: 0.7508\nEpoch 4/100\n891/891 [==============================] - 0s 377us/step - loss: 0.5030 - acc: 0.7587\nEpoch 5/100\n891/891 [==============================] - 0s 379us/step - loss: 0.4839 - acc: 0.7912\nEpoch 6/100\n891/891 [==============================] - 0s 380us/step - loss: 0.4828 - acc: 0.7969\nEpoch 7/100\n891/891 [==============================] - 0s 385us/step - loss: 0.4721 - acc: 0.7991\nEpoch 8/100\n891/891 [==============================] - 0s 379us/step - loss: 0.4655 - acc: 0.7957\nEpoch 9/100\n891/891 [==============================] - 0s 382us/step - loss: 0.4554 - acc: 0.7946\nEpoch 10/100\n891/891 [==============================] - 0s 374us/step - loss: 0.4730 - acc: 0.7991\nEpoch 11/100\n891/891 [==============================] - 0s 396us/step - loss: 0.4707 - acc: 0.7946\nEpoch 12/100\n891/891 [==============================] - 0s 384us/step - loss: 0.4607 - acc: 0.8002\nEpoch 13/100\n891/891 [==============================] - 0s 398us/step - loss: 0.4517 - acc: 0.8047\nEpoch 14/100\n891/891 [==============================] - 0s 416us/step - loss: 0.4711 - acc: 0.7969\nEpoch 15/100\n891/891 [==============================] - 0s 408us/step - loss: 0.4488 - acc: 0.8070\nEpoch 16/100\n891/891 [==============================] - 0s 411us/step - loss: 0.4502 - acc: 0.8081\nEpoch 17/100\n891/891 [==============================] - 0s 424us/step - loss: 0.4461 - acc: 0.8081\nEpoch 18/100\n891/891 [==============================] - 0s 410us/step - loss: 0.4489 - acc: 0.8137\nEpoch 19/100\n891/891 [==============================] - 0s 414us/step - loss: 0.4463 - acc: 0.8114\nEpoch 20/100\n891/891 [==============================] - 0s 410us/step - loss: 0.4421 - acc: 0.8047\nEpoch 21/100\n891/891 [==============================] - 0s 402us/step - loss: 0.4428 - acc: 0.8047\nEpoch 22/100\n891/891 [==============================] - 0s 422us/step - loss: 0.4364 - acc: 0.8036\nEpoch 23/100\n891/891 [==============================] - 0s 413us/step - loss: 0.4478 - acc: 0.8137\nEpoch 24/100\n891/891 [==============================] - 0s 411us/step - loss: 0.4473 - acc: 0.8114\nEpoch 25/100\n891/891 [==============================] - 0s 419us/step - loss: 0.4489 - acc: 0.8159\nEpoch 26/100\n891/891 [==============================] - 0s 411us/step - loss: 0.4370 - acc: 0.8137\nEpoch 27/100\n891/891 [==============================] - 0s 405us/step - loss: 0.4275 - acc: 0.8114\nEpoch 28/100\n891/891 [==============================] - 0s 397us/step - loss: 0.4358 - acc: 0.8215\nEpoch 29/100\n891/891 [==============================] - 0s 379us/step - loss: 0.4364 - acc: 0.8126\nEpoch 30/100\n891/891 [==============================] - 0s 386us/step - loss: 0.4378 - acc: 0.8159\nEpoch 31/100\n891/891 [==============================] - 0s 420us/step - loss: 0.4378 - acc: 0.8193\nEpoch 32/100\n891/891 [==============================] - 0s 396us/step - loss: 0.4214 - acc: 0.8215\nEpoch 33/100\n891/891 [==============================] - 0s 428us/step - loss: 0.4367 - acc: 0.8204\nEpoch 34/100\n891/891 [==============================] - 0s 408us/step - loss: 0.4318 - acc: 0.8182\nEpoch 35/100\n891/891 [==============================] - 0s 384us/step - loss: 0.4430 - acc: 0.8126\nEpoch 36/100\n891/891 [==============================] - 0s 423us/step - loss: 0.4284 - acc: 0.8227\nEpoch 37/100\n891/891 [==============================] - 0s 410us/step - loss: 0.4422 - acc: 0.8126\nEpoch 38/100\n891/891 [==============================] - 0s 410us/step - loss: 0.4366 - acc: 0.8238\nEpoch 39/100\n891/891 [==============================] - 0s 407us/step - loss: 0.4196 - acc: 0.8159\nEpoch 40/100\n891/891 [==============================] - 0s 413us/step - loss: 0.4385 - acc: 0.8092\nEpoch 41/100\n891/891 [==============================] - 0s 431us/step - loss: 0.4372 - acc: 0.8283\nEpoch 42/100\n891/891 [==============================] - 0s 436us/step - loss: 0.4346 - acc: 0.8260\nEpoch 43/100\n891/891 [==============================] - 0s 393us/step - loss: 0.4393 - acc: 0.8238\nEpoch 44/100\n891/891 [==============================] - 0s 394us/step - loss: 0.4273 - acc: 0.8215\nEpoch 45/100\n891/891 [==============================] - 0s 387us/step - loss: 0.4230 - acc: 0.8283\nEpoch 46/100\n891/891 [==============================] - 0s 380us/step - loss: 0.4344 - acc: 0.8260\nEpoch 47/100\n891/891 [==============================] - 0s 387us/step - loss: 0.4206 - acc: 0.8272\nEpoch 48/100\n891/891 [==============================] - 0s 401us/step - loss: 0.4327 - acc: 0.8249\nEpoch 49/100\n891/891 [==============================] - 0s 379us/step - loss: 0.4447 - acc: 0.8215\nEpoch 50/100\n891/891 [==============================] - 0s 385us/step - loss: 0.4315 - acc: 0.8182\nEpoch 51/100\n891/891 [==============================] - 0s 384us/step - loss: 0.4308 - acc: 0.8137\nEpoch 52/100\n891/891 [==============================] - 0s 379us/step - loss: 0.4334 - acc: 0.8283\nEpoch 53/100\n891/891 [==============================] - 0s 386us/step - loss: 0.4283 - acc: 0.8182\nEpoch 54/100\n891/891 [==============================] - 0s 379us/step - loss: 0.4265 - acc: 0.8305\nEpoch 55/100\n891/891 [==============================] - 0s 389us/step - loss: 0.4233 - acc: 0.8215\nEpoch 56/100\n891/891 [==============================] - 0s 397us/step - loss: 0.4357 - acc: 0.8182\nEpoch 57/100\n891/891 [==============================] - 0s 391us/step - loss: 0.4267 - acc: 0.8204\nEpoch 58/100\n891/891 [==============================] - 0s 383us/step - loss: 0.4209 - acc: 0.8283\nEpoch 59/100\n891/891 [==============================] - 0s 393us/step - loss: 0.4231 - acc: 0.8305\nEpoch 60/100\n891/891 [==============================] - 0s 387us/step - loss: 0.4212 - acc: 0.8227\nEpoch 61/100\n891/891 [==============================] - 0s 404us/step - loss: 0.4256 - acc: 0.8328\nEpoch 62/100\n891/891 [==============================] - 0s 387us/step - loss: 0.4323 - acc: 0.8294\nEpoch 63/100\n891/891 [==============================] - 0s 385us/step - loss: 0.4465 - acc: 0.8215\nEpoch 64/100\n891/891 [==============================] - 0s 392us/step - loss: 0.4228 - acc: 0.8249\nEpoch 65/100\n891/891 [==============================] - 0s 398us/step - loss: 0.4309 - acc: 0.8249\nEpoch 66/100\n891/891 [==============================] - 0s 418us/step - loss: 0.4336 - acc: 0.8350\nEpoch 67/100\n891/891 [==============================] - 0s 453us/step - loss: 0.4290 - acc: 0.8272\nEpoch 68/100\n891/891 [==============================] - 0s 389us/step - loss: 0.4387 - acc: 0.8249\nEpoch 69/100\n891/891 [==============================] - 0s 414us/step - loss: 0.4412 - acc: 0.8305\nEpoch 70/100\n891/891 [==============================] - 0s 388us/step - loss: 0.4431 - acc: 0.8316\nEpoch 71/100\n891/891 [==============================] - 0s 415us/step - loss: 0.4530 - acc: 0.8339\nEpoch 72/100\n891/891 [==============================] - 0s 414us/step - loss: 0.4313 - acc: 0.8283\nEpoch 73/100\n891/891 [==============================] - 0s 415us/step - loss: 0.4389 - acc: 0.8361\nEpoch 74/100\n891/891 [==============================] - 0s 408us/step - loss: 0.4305 - acc: 0.8406\nEpoch 75/100\n891/891 [==============================] - 0s 430us/step - loss: 0.4384 - acc: 0.8238\nEpoch 76/100\n891/891 [==============================] - 0s 405us/step - loss: 0.4264 - acc: 0.8283\nEpoch 77/100\n891/891 [==============================] - 0s 407us/step - loss: 0.4459 - acc: 0.8238\nEpoch 78/100\n891/891 [==============================] - 0s 443us/step - loss: 0.4290 - acc: 0.8294\nEpoch 79/100\n891/891 [==============================] - 0s 413us/step - loss: 0.4437 - acc: 0.8294\nEpoch 80/100\n891/891 [==============================] - 0s 389us/step - loss: 0.4304 - acc: 0.8294\nEpoch 81/100\n891/891 [==============================] - 0s 420us/step - loss: 0.4435 - acc: 0.8316\nEpoch 82/100\n891/891 [==============================] - 0s 398us/step - loss: 0.4359 - acc: 0.8339\nEpoch 83/100\n891/891 [==============================] - 0s 491us/step - loss: 0.4251 - acc: 0.8316\nEpoch 84/100\n891/891 [==============================] - 0s 373us/step - loss: 0.4284 - acc: 0.8316\nEpoch 85/100\n891/891 [==============================] - 0s 372us/step - loss: 0.4458 - acc: 0.8406\nEpoch 86/100\n891/891 [==============================] - 0s 391us/step - loss: 0.4510 - acc: 0.8350\nEpoch 87/100\n891/891 [==============================] - 0s 375us/step - loss: 0.4368 - acc: 0.8272\nEpoch 88/100\n891/891 [==============================] - 0s 392us/step - loss: 0.4452 - acc: 0.8305\nEpoch 89/100\n891/891 [==============================] - 0s 388us/step - loss: 0.4513 - acc: 0.8361\nEpoch 90/100\n891/891 [==============================] - 0s 398us/step - loss: 0.4434 - acc: 0.8283\nEpoch 91/100\n891/891 [==============================] - 0s 417us/step - loss: 0.4360 - acc: 0.8294\nEpoch 92/100\n891/891 [==============================] - 0s 416us/step - loss: 0.4360 - acc: 0.8294\nEpoch 93/100\n891/891 [==============================] - 0s 383us/step - loss: 0.4329 - acc: 0.8361\nEpoch 94/100\n891/891 [==============================] - 0s 387us/step - loss: 0.4279 - acc: 0.8429\nEpoch 95/100\n891/891 [==============================] - 0s 392us/step - loss: 0.4460 - acc: 0.8294\nEpoch 96/100\n891/891 [==============================] - 0s 408us/step - loss: 0.4339 - acc: 0.8350\nEpoch 97/100\n891/891 [==============================] - 0s 410us/step - loss: 0.4279 - acc: 0.8373\nEpoch 98/100\n891/891 [==============================] - 0s 411us/step - loss: 0.4330 - acc: 0.8384\nEpoch 99/100\n891/891 [==============================] - 0s 413us/step - loss: 0.4277 - acc: 0.8373\nEpoch 100/100\n891/891 [==============================] - 0s 410us/step - loss: 0.4220 - acc: 0.8418\n"
}
]
},
{
"metadata": {
"scrolled": false,
"trusted": true
},
"cell_type": "code",
"source": "# print(model.metrics_names)\n\nplt.plot(hist.history['acc'], 'b-', label='acc' )\nplt.plot(hist.history['loss'], 'r-', label='loss' )\nplt.xlabel('epochs')\nplt.legend()\nplt.show()",
"execution_count": 73,
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": "<matplotlib.figure.Figure at 0x7f8f83271e10>"
},
"metadata": {},
"output_type": "display_data"
}
]
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "result = pred.argmax(axis=1)",
"execution_count": 74,
"outputs": []
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Submission file:"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "submission = pd.DataFrame({'PassengerId': test.index, 'Survived': result})\nsubmission.to_csv('submission.csv', index=False)",
"execution_count": 75,
"outputs": []
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "",
"execution_count": null,
"outputs": []
}
],
"metadata": {
"gist": {
"id": "",
"data": {
"description": "Kaggle:Titanic",
"public": true
}
},
"kernelspec": {
"name": "py36",
"display_name": "py36",
"language": "python"
},
"language_info": {
"name": "python",
"version": "3.6.4",
"mimetype": "text/x-python",
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python",
"file_extension": ".py"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment