import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
np.random.seed(123)
from tensorflow import set_random_seed
set_random_seed(123)
train = pd.read_csv('titanic/train.csv', index_col=0)
test = pd.read_csv('titanic/test.csv', index_col=0)
train.head()
Survived | Pclass | Name | Sex | Age | SibSp | Parch | Ticket | Fare | Cabin | Embarked | |
---|---|---|---|---|---|---|---|---|---|---|---|
PassengerId | |||||||||||
1 | 0 | 3 | Braund, Mr. Owen Harris | male | 22.0 | 1 | 0 | A/5 21171 | 7.2500 | NaN | S |
2 | 1 | 1 | Cumings, Mrs. John Bradley (Florence Briggs Th... | female | 38.0 | 1 | 0 | PC 17599 | 71.2833 | C85 | C |
3 | 1 | 3 | Heikkinen, Miss. Laina | female | 26.0 | 0 | 0 | STON/O2. 3101282 | 7.9250 | NaN | S |
4 | 1 | 1 | Futrelle, Mrs. Jacques Heath (Lily May Peel) | female | 35.0 | 1 | 0 | 113803 | 53.1000 | C123 | S |
5 | 0 | 3 | Allen, Mr. William Henry | male | 35.0 | 0 | 0 | 373450 | 8.0500 | NaN | S |
train_tmp = train.drop(['Survived', 'Ticket'], axis=1)
test_tmp = test.drop(['Ticket'], axis=1)
df = pd.concat([train_tmp, test_tmp])
df.info()
<class 'pandas.core.frame.DataFrame'> Int64Index: 1309 entries, 1 to 1309 Data columns (total 9 columns): Pclass 1309 non-null int64 Name 1309 non-null object Sex 1309 non-null object Age 1046 non-null float64 SibSp 1309 non-null int64 Parch 1309 non-null int64 Fare 1308 non-null float64 Cabin 295 non-null object Embarked 1307 non-null object dtypes: float64(2), int64(3), object(4) memory usage: 102.3+ KB
# Name to Title
df = df.assign(Title=df.Name.str.extract(' ([A-Za-z]+)\..', expand=True))
title_list = df.Title.unique()
print(title_list)
['Mr' 'Mrs' 'Miss' 'Master' 'Don' 'Rev' 'Dr' 'Mme' 'Ms' 'Major' 'Lady' 'Sir' 'Mlle' 'Col' 'Capt' 'Countess' 'Jonkheer' 'Dona']
# Title to Number(0-17)
df.Title = df.Title.replace(df.Title.unique(), np.arange(len(df.Title.unique())))
# Drop Name column
df = df.drop(['Name'], axis=1)
df.head()
Pclass | Sex | Age | SibSp | Parch | Fare | Cabin | Embarked | Title | |
---|---|---|---|---|---|---|---|---|---|
PassengerId | |||||||||
1 | 3 | male | 22.0 | 1 | 0 | 7.2500 | NaN | S | Mr |
2 | 1 | female | 38.0 | 1 | 0 | 71.2833 | C85 | C | Mrs |
3 | 3 | female | 26.0 | 0 | 0 | 7.9250 | NaN | S | Miss |
4 | 1 | female | 35.0 | 1 | 0 | 53.1000 | C123 | S | Mrs |
5 | 3 | male | 35.0 | 0 | 0 | 8.0500 | NaN | S | Mr |
df.Sex = df.Sex.replace({'male': 0, 'female': 1})
df = df.assign(Cabin=df.Cabin.str[0])
cabin_list = df.Cabin.unique()
df.Cabin = df.Cabin.replace(df.Cabin.str[0].unique(), np.arange(len(df.Cabin.str[0].unique())))
print(cabin_list)
print(df.Cabin.unique())
[nan 'C' 'E' 'G' 'D' 'A' 'B' 'F' 'T'] [0 1 2 3 4 5 6 7 8]
df.Embarked.unique()
array(['S', 'C', 'Q', nan], dtype=object)
df.Embarked = df.Embarked.replace({'S':0, 'C':1, 'Q':2})
Z = (x - x.mean) / x.std
N = (x - x.min)/(x.max - x.min)
sklearn.preprocessing.MinMaxScaler causes error with Null data.
# Normalize Function
def normalize(df_col):
df_col = (df_col - df_col.min()) / (df_col.max() - df_col.min())
return df_col
# Standardization(zscore)
def zscore(df_col):
df_col = (df_col - df_col.mean()) / df_col.std()
return df_col
df.Age = zscore(df.Age)
df.Fare = zscore(df.Fare)
# df.Age = normalize(df.Age)
# df.Fare = normalize(df.Fare)
# for col in df.columns:
# df[col] = zscore(df[col])
df.describe()
Pclass | Sex | Age | SibSp | Parch | Fare | Cabin | Embarked | Title_Capt | Title_Col | ... | Title_Major | Title_Master | Title_Miss | Title_Mlle | Title_Mme | Title_Mr | Title_Mrs | Title_Ms | Title_Rev | Title_Sir | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
count | 1309.000000 | 1309.000000 | 1.046000e+03 | 1309.000000 | 1309.000000 | 1.308000e+03 | 1309.000000 | 1307.000000 | 1309.000000 | 1309.000000 | ... | 1309.000000 | 1309.000000 | 1309.000000 | 1309.000000 | 1309.000000 | 1309.000000 | 1309.000000 | 1309.000000 | 1309.000000 | 1309.000000 |
mean | 2.294882 | 0.355997 | 9.488904e-17 | 0.498854 | 0.385027 | -6.049357e-16 | 0.786860 | 0.394797 | 0.000764 | 0.003056 | ... | 0.001528 | 0.046600 | 0.198625 | 0.001528 | 0.000764 | 0.578304 | 0.150497 | 0.001528 | 0.006112 | 0.000764 |
std | 0.837836 | 0.478997 | 1.000000e+00 | 1.041658 | 0.865560 | 1.000000e+00 | 1.794388 | 0.653817 | 0.027639 | 0.055216 | ... | 0.039073 | 0.210862 | 0.399117 | 0.039073 | 0.027639 | 0.494019 | 0.357694 | 0.039073 | 0.077967 | 0.027639 |
min | 1.000000 | 0.000000 | -2.061342e+00 | 0.000000 | 0.000000 | -6.432832e-01 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | ... | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 |
25% | 2.000000 | 0.000000 | -6.161683e-01 | 0.000000 | 0.000000 | -4.907329e-01 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | ... | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 |
50% | 3.000000 | 0.000000 | -1.305123e-01 | 0.000000 | 0.000000 | -3.640217e-01 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | ... | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 1.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 |
75% | 3.000000 | 1.000000 | 6.326615e-01 | 1.000000 | 0.000000 | -3.903654e-02 | 0.000000 | 1.000000 | 0.000000 | 0.000000 | ... | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 1.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 |
max | 3.000000 | 1.000000 | 3.477218e+00 | 8.000000 | 9.000000 | 9.255140e+00 | 8.000000 | 2.000000 | 1.000000 | 1.000000 | ... | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 |
8 rows × 26 columns
df0 = df.copy()
df0.info()
<class 'pandas.core.frame.DataFrame'> Int64Index: 1309 entries, 1 to 1309 Data columns (total 26 columns): Pclass 1309 non-null int64 Sex 1309 non-null int64 Age 1046 non-null float64 SibSp 1309 non-null int64 Parch 1309 non-null int64 Fare 1308 non-null float64 Cabin 1309 non-null int64 Embarked 1307 non-null float64 Title_Capt 1309 non-null uint8 Title_Col 1309 non-null uint8 Title_Countess 1309 non-null uint8 Title_Don 1309 non-null uint8 Title_Dona 1309 non-null uint8 Title_Dr 1309 non-null uint8 Title_Jonkheer 1309 non-null uint8 Title_Lady 1309 non-null uint8 Title_Major 1309 non-null uint8 Title_Master 1309 non-null uint8 Title_Miss 1309 non-null uint8 Title_Mlle 1309 non-null uint8 Title_Mme 1309 non-null uint8 Title_Mr 1309 non-null uint8 Title_Mrs 1309 non-null uint8 Title_Ms 1309 non-null uint8 Title_Rev 1309 non-null uint8 Title_Sir 1309 non-null uint8 dtypes: float64(3), int64(5), uint8(18) memory usage: 115.0 KB
Age_null = df[df.Age.isnull()]
df = df[df.Age.notnull()]
Embarked_null = df[df.Embarked.isnull()]
df = df[df.Embarked.notnull()]
Fare_null = df[df.Fare.isnull()]
df = df[df.Fare.notnull()]
print(df.shape)
df.info()
(1043, 26) <class 'pandas.core.frame.DataFrame'> Int64Index: 1043 entries, 1 to 1307 Data columns (total 26 columns): Pclass 1043 non-null int64 Sex 1043 non-null int64 Age 1043 non-null float64 SibSp 1043 non-null int64 Parch 1043 non-null int64 Fare 1043 non-null float64 Cabin 1043 non-null int64 Embarked 1043 non-null float64 Title_Capt 1043 non-null uint8 Title_Col 1043 non-null uint8 Title_Countess 1043 non-null uint8 Title_Don 1043 non-null uint8 Title_Dona 1043 non-null uint8 Title_Dr 1043 non-null uint8 Title_Jonkheer 1043 non-null uint8 Title_Lady 1043 non-null uint8 Title_Major 1043 non-null uint8 Title_Master 1043 non-null uint8 Title_Miss 1043 non-null uint8 Title_Mlle 1043 non-null uint8 Title_Mme 1043 non-null uint8 Title_Mr 1043 non-null uint8 Title_Mrs 1043 non-null uint8 Title_Ms 1043 non-null uint8 Title_Rev 1043 non-null uint8 Title_Sir 1043 non-null uint8 dtypes: float64(3), int64(5), uint8(18) memory usage: 91.7 KB
from keras.models import Sequential
from keras.layers import Flatten, Dense, Dropout, BatchNormalization
# model for Fare, Embarked, Age
def fill_data(col):
n_cols = len(df.columns) - 1
num = len(df[col].unique())
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(n_cols,)))
model.add(Dropout(0.5))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.5))
if col == 'Embarked':
model.add(Dense(num, activation='softmax'))
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['acc'])
else: # 'Fare', 'Age'
model.add(Dense(1, activation='linear'))
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
data = df.drop([col], axis=1)
epochs = 100
hist = model.fit(data, df[col], epochs=epochs, batch_size=32)
null_data = df0[df0[col].isnull()]
null_data = null_data.drop([col], axis=1)
pred = model.predict(null_data)
if col == 'Embarked':
pred = pred.argmax(axis=1)
plt.plot(hist.history['acc'], 'b-', label='acc' )
plt.plot(hist.history['loss'], 'r-', label='loss' )
plt.xlabel('epochs')
plt.legend()
plt.show()
pred = pred.reshape(-1, )
idx = df0[df0[col].isnull()].index.values
for n, i in enumerate(idx):
df0.loc[i, col] = pred[n]
fill_data('Embarked') # id:62,830
Epoch 1/100 1043/1043 [==============================] - 3s 3ms/step - loss: 1.0055 - acc: 0.5350 Epoch 2/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.7874 - acc: 0.7143 Epoch 3/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.7494 - acc: 0.7172 Epoch 4/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.7250 - acc: 0.7363 Epoch 5/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.7016 - acc: 0.7498 Epoch 6/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.7047 - acc: 0.7402 Epoch 7/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.7115 - acc: 0.7507 Epoch 8/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.6749 - acc: 0.7536 Epoch 9/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.6990 - acc: 0.7507 Epoch 10/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6809 - acc: 0.7498 Epoch 11/100 1043/1043 [==============================] - 0s 84us/step - loss: 0.6844 - acc: 0.7488 Epoch 12/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6618 - acc: 0.7450 Epoch 13/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.6694 - acc: 0.7670 Epoch 14/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6662 - acc: 0.7565 Epoch 15/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6535 - acc: 0.7546 Epoch 16/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6508 - acc: 0.7603 Epoch 17/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6579 - acc: 0.7565 Epoch 18/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6616 - acc: 0.7603 Epoch 19/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6437 - acc: 0.7546 Epoch 20/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6559 - acc: 0.7517 Epoch 21/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6379 - acc: 0.7526 Epoch 22/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.6338 - acc: 0.7593 Epoch 23/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6266 - acc: 0.7632 Epoch 24/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.6426 - acc: 0.7565 Epoch 25/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6347 - acc: 0.7603 Epoch 26/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6419 - acc: 0.7622 Epoch 27/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6307 - acc: 0.7555 Epoch 28/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.6284 - acc: 0.7584 Epoch 29/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6143 - acc: 0.7613 Epoch 30/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6245 - acc: 0.7536 Epoch 31/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6222 - acc: 0.7718 Epoch 32/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6129 - acc: 0.7584 Epoch 33/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6241 - acc: 0.7555 Epoch 34/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6147 - acc: 0.7555 Epoch 35/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6163 - acc: 0.7546 Epoch 36/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6133 - acc: 0.7584 Epoch 37/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6204 - acc: 0.7632 Epoch 38/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6229 - acc: 0.7670 Epoch 39/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6082 - acc: 0.7632 Epoch 40/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6227 - acc: 0.7728 Epoch 41/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6098 - acc: 0.7622 Epoch 42/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6039 - acc: 0.7728 Epoch 43/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6030 - acc: 0.7651 Epoch 44/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5946 - acc: 0.7680 Epoch 45/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6139 - acc: 0.7661 Epoch 46/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5854 - acc: 0.7776 Epoch 47/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6018 - acc: 0.7651 Epoch 48/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.6061 - acc: 0.7661 Epoch 49/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6083 - acc: 0.7593 Epoch 50/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.5996 - acc: 0.7709 Epoch 51/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5891 - acc: 0.7728 Epoch 52/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5972 - acc: 0.7689 Epoch 53/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5938 - acc: 0.7699 Epoch 54/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.5845 - acc: 0.7632 Epoch 55/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.5719 - acc: 0.7689 Epoch 56/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.5995 - acc: 0.7574 Epoch 57/100 1043/1043 [==============================] - 0s 85us/step - loss: 0.5924 - acc: 0.7709 Epoch 58/100 1043/1043 [==============================] - 0s 81us/step - loss: 0.5937 - acc: 0.7632 Epoch 59/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5977 - acc: 0.7593 Epoch 60/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.5748 - acc: 0.7756 Epoch 61/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5764 - acc: 0.7632 Epoch 62/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5753 - acc: 0.7737 Epoch 63/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.5815 - acc: 0.7651 Epoch 64/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5864 - acc: 0.7766 Epoch 65/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5971 - acc: 0.7603 Epoch 66/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5830 - acc: 0.7833 Epoch 67/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.5780 - acc: 0.7747 Epoch 68/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5643 - acc: 0.7804 Epoch 69/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5781 - acc: 0.7718 Epoch 70/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.5705 - acc: 0.7718 Epoch 71/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5851 - acc: 0.7728 Epoch 72/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.5708 - acc: 0.7680 Epoch 73/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5827 - acc: 0.7728 Epoch 74/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.5755 - acc: 0.7737 Epoch 75/100 1043/1043 [==============================] - 0s 84us/step - loss: 0.5739 - acc: 0.7622 Epoch 76/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.5762 - acc: 0.7651 Epoch 77/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.5853 - acc: 0.7689 Epoch 78/100 1043/1043 [==============================] - 0s 82us/step - loss: 0.5741 - acc: 0.7747 Epoch 79/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.5637 - acc: 0.7718 Epoch 80/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5650 - acc: 0.7814 Epoch 81/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.5612 - acc: 0.7651 Epoch 82/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.5682 - acc: 0.7824 Epoch 83/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5617 - acc: 0.7785 Epoch 84/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5711 - acc: 0.7728 Epoch 85/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5623 - acc: 0.7756 Epoch 86/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5610 - acc: 0.7718 Epoch 87/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5796 - acc: 0.7699 Epoch 88/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.5669 - acc: 0.7881 Epoch 89/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5708 - acc: 0.7718 Epoch 90/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5665 - acc: 0.7747 Epoch 91/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5663 - acc: 0.7756 Epoch 92/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5630 - acc: 0.7785 Epoch 93/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5667 - acc: 0.7737 Epoch 94/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5638 - acc: 0.7699 Epoch 95/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5723 - acc: 0.7728 Epoch 96/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.5578 - acc: 0.7776 Epoch 97/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5520 - acc: 0.7814 Epoch 98/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5544 - acc: 0.7728 Epoch 99/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5672 - acc: 0.7804 Epoch 100/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.5574 - acc: 0.7718
fill_data('Fare') # id:1044
Epoch 1/100 1043/1043 [==============================] - 3s 3ms/step - loss: 1.4221 - mean_absolute_error: 0.7019 Epoch 2/100 1043/1043 [==============================] - 0s 72us/step - loss: 1.1943 - mean_absolute_error: 0.6114 Epoch 3/100 1043/1043 [==============================] - 0s 71us/step - loss: 1.1357 - mean_absolute_error: 0.5726 Epoch 4/100 1043/1043 [==============================] - 0s 71us/step - loss: 1.0853 - mean_absolute_error: 0.5431 Epoch 5/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.9761 - mean_absolute_error: 0.5245 Epoch 6/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.9486 - mean_absolute_error: 0.5070 Epoch 7/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.9139 - mean_absolute_error: 0.5001 Epoch 8/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.9015 - mean_absolute_error: 0.4918 Epoch 9/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.8877 - mean_absolute_error: 0.4892 Epoch 10/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.8116 - mean_absolute_error: 0.4611 Epoch 11/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.8339 - mean_absolute_error: 0.4681 Epoch 12/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.8145 - mean_absolute_error: 0.4652 Epoch 13/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.8042 - mean_absolute_error: 0.4531 Epoch 14/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.8021 - mean_absolute_error: 0.4549 Epoch 15/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.7902 - mean_absolute_error: 0.4480 Epoch 16/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.7817 - mean_absolute_error: 0.4453 Epoch 17/100 1043/1043 [==============================] - 0s 82us/step - loss: 0.7609 - mean_absolute_error: 0.4425 Epoch 18/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.7748 - mean_absolute_error: 0.4440 Epoch 19/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.7385 - mean_absolute_error: 0.4333 Epoch 20/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.7097 - mean_absolute_error: 0.4441 Epoch 21/100 1043/1043 [==============================] - 0s 83us/step - loss: 0.7454 - mean_absolute_error: 0.4313 Epoch 22/100 1043/1043 [==============================] - 0s 81us/step - loss: 0.7190 - mean_absolute_error: 0.4309 Epoch 23/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.7325 - mean_absolute_error: 0.4278 Epoch 24/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.7364 - mean_absolute_error: 0.4274 Epoch 25/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.7144 - mean_absolute_error: 0.4173 Epoch 26/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6903 - mean_absolute_error: 0.4143 Epoch 27/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6572 - mean_absolute_error: 0.4158 Epoch 28/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6872 - mean_absolute_error: 0.4148 Epoch 29/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.6543 - mean_absolute_error: 0.4117 Epoch 30/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.6758 - mean_absolute_error: 0.4124 Epoch 31/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6529 - mean_absolute_error: 0.3985 Epoch 32/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.6759 - mean_absolute_error: 0.4098 Epoch 33/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.6362 - mean_absolute_error: 0.3984 Epoch 34/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6660 - mean_absolute_error: 0.3989 Epoch 35/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6919 - mean_absolute_error: 0.4103 Epoch 36/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6787 - mean_absolute_error: 0.4101 Epoch 37/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6319 - mean_absolute_error: 0.3989 Epoch 38/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6419 - mean_absolute_error: 0.3884 Epoch 39/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.6641 - mean_absolute_error: 0.4035 Epoch 40/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6466 - mean_absolute_error: 0.3998 Epoch 41/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6470 - mean_absolute_error: 0.3913 Epoch 42/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6070 - mean_absolute_error: 0.3885 Epoch 43/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6797 - mean_absolute_error: 0.3988 Epoch 44/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6475 - mean_absolute_error: 0.3909 Epoch 45/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6224 - mean_absolute_error: 0.3936 Epoch 46/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6888 - mean_absolute_error: 0.4032 Epoch 47/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.5836 - mean_absolute_error: 0.3787 Epoch 48/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.5982 - mean_absolute_error: 0.3795 Epoch 49/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.5953 - mean_absolute_error: 0.3827 Epoch 50/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.6295 - mean_absolute_error: 0.3795 Epoch 51/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.6180 - mean_absolute_error: 0.3689 Epoch 52/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.6241 - mean_absolute_error: 0.3795 Epoch 53/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.5616 - mean_absolute_error: 0.3802 Epoch 54/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6189 - mean_absolute_error: 0.3962 Epoch 55/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.6373 - mean_absolute_error: 0.3841 Epoch 56/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6313 - mean_absolute_error: 0.3833 Epoch 57/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.6143 - mean_absolute_error: 0.3866 Epoch 58/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5706 - mean_absolute_error: 0.3596 Epoch 59/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5931 - mean_absolute_error: 0.3790 Epoch 60/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6212 - mean_absolute_error: 0.3745 Epoch 61/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6297 - mean_absolute_error: 0.3908 Epoch 62/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.5912 - mean_absolute_error: 0.3655 Epoch 63/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5728 - mean_absolute_error: 0.3689 Epoch 64/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5721 - mean_absolute_error: 0.3706 Epoch 65/100 1043/1043 [==============================] - 0s 87us/step - loss: 0.5948 - mean_absolute_error: 0.3825 Epoch 66/100 1043/1043 [==============================] - 0s 64us/step - loss: 0.5912 - mean_absolute_error: 0.3753 Epoch 67/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5784 - mean_absolute_error: 0.3654 Epoch 68/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5919 - mean_absolute_error: 0.3583 Epoch 69/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.5631 - mean_absolute_error: 0.3691 Epoch 70/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.5422 - mean_absolute_error: 0.3611 Epoch 71/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5764 - mean_absolute_error: 0.3663 Epoch 72/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5817 - mean_absolute_error: 0.3615 Epoch 73/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.5965 - mean_absolute_error: 0.3790 Epoch 74/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.5709 - mean_absolute_error: 0.3526 Epoch 75/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.5948 - mean_absolute_error: 0.3538 Epoch 76/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.5885 - mean_absolute_error: 0.3698 Epoch 77/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5757 - mean_absolute_error: 0.3622 Epoch 78/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5364 - mean_absolute_error: 0.3449 Epoch 79/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5897 - mean_absolute_error: 0.3722 Epoch 80/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5624 - mean_absolute_error: 0.3596 Epoch 81/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.5456 - mean_absolute_error: 0.3607 Epoch 82/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6008 - mean_absolute_error: 0.3706 Epoch 83/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5185 - mean_absolute_error: 0.3527 Epoch 84/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5703 - mean_absolute_error: 0.3559 Epoch 85/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5632 - mean_absolute_error: 0.3605 Epoch 86/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5384 - mean_absolute_error: 0.3561 Epoch 87/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5601 - mean_absolute_error: 0.3659 Epoch 88/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5636 - mean_absolute_error: 0.3586 Epoch 89/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5919 - mean_absolute_error: 0.3663 Epoch 90/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5590 - mean_absolute_error: 0.3580 Epoch 91/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.5652 - mean_absolute_error: 0.3545 Epoch 92/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5613 - mean_absolute_error: 0.3595 Epoch 93/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.4973 - mean_absolute_error: 0.3472 Epoch 94/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.5177 - mean_absolute_error: 0.3378 Epoch 95/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5458 - mean_absolute_error: 0.3462 Epoch 96/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.5295 - mean_absolute_error: 0.3496 Epoch 97/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5514 - mean_absolute_error: 0.3532 Epoch 98/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5851 - mean_absolute_error: 0.3604 Epoch 99/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5378 - mean_absolute_error: 0.3486 Epoch 100/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.5397 - mean_absolute_error: 0.3539
fill_data('Age') # id: 6,18,20,27,29,30
Epoch 1/100 1043/1043 [==============================] - 3s 3ms/step - loss: 1.2363 - mean_absolute_error: 0.8609 Epoch 2/100 1043/1043 [==============================] - 0s 73us/step - loss: 1.0649 - mean_absolute_error: 0.7896 Epoch 3/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.9711 - mean_absolute_error: 0.7641 Epoch 4/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.9554 - mean_absolute_error: 0.7523 Epoch 5/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.9089 - mean_absolute_error: 0.7359 Epoch 6/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.8579 - mean_absolute_error: 0.7222 Epoch 7/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.8468 - mean_absolute_error: 0.7151 Epoch 8/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.8436 - mean_absolute_error: 0.7126 Epoch 9/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.8104 - mean_absolute_error: 0.7017 Epoch 10/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.8224 - mean_absolute_error: 0.7040 Epoch 11/100 1043/1043 [==============================] - 0s 79us/step - loss: 0.7763 - mean_absolute_error: 0.6906 Epoch 12/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.7487 - mean_absolute_error: 0.6867 Epoch 13/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.7893 - mean_absolute_error: 0.6902 Epoch 14/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.7305 - mean_absolute_error: 0.6676 Epoch 15/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.7276 - mean_absolute_error: 0.6674 Epoch 16/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.7351 - mean_absolute_error: 0.6738 Epoch 17/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.7433 - mean_absolute_error: 0.6771 Epoch 18/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.7257 - mean_absolute_error: 0.6712 Epoch 19/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6910 - mean_absolute_error: 0.6563 Epoch 20/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.7006 - mean_absolute_error: 0.6587 Epoch 21/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.7131 - mean_absolute_error: 0.6643 Epoch 22/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6795 - mean_absolute_error: 0.6518 Epoch 23/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.7009 - mean_absolute_error: 0.6589 Epoch 24/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.7171 - mean_absolute_error: 0.6634 Epoch 25/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.6655 - mean_absolute_error: 0.6454 Epoch 26/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6668 - mean_absolute_error: 0.6394 Epoch 27/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.6807 - mean_absolute_error: 0.6520 Epoch 28/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.6471 - mean_absolute_error: 0.6286 Epoch 29/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6829 - mean_absolute_error: 0.6472 Epoch 30/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.6564 - mean_absolute_error: 0.6366 Epoch 31/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.6962 - mean_absolute_error: 0.6560 Epoch 32/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.6751 - mean_absolute_error: 0.6465 Epoch 33/100 1043/1043 [==============================] - 0s 77us/step - loss: 0.6519 - mean_absolute_error: 0.6342 Epoch 34/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6623 - mean_absolute_error: 0.6395 Epoch 35/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.6572 - mean_absolute_error: 0.6296 Epoch 36/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6631 - mean_absolute_error: 0.6395 Epoch 37/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6516 - mean_absolute_error: 0.6363 Epoch 38/100 1043/1043 [==============================] - 0s 82us/step - loss: 0.6575 - mean_absolute_error: 0.6341 Epoch 39/100 1043/1043 [==============================] - 0s 80us/step - loss: 0.6104 - mean_absolute_error: 0.6123 Epoch 40/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.6655 - mean_absolute_error: 0.6360 Epoch 41/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.6445 - mean_absolute_error: 0.6322 Epoch 42/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6409 - mean_absolute_error: 0.6365 Epoch 43/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.6692 - mean_absolute_error: 0.6357 Epoch 44/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6239 - mean_absolute_error: 0.6194 Epoch 45/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6576 - mean_absolute_error: 0.6377 Epoch 46/100 1043/1043 [==============================] - 0s 75us/step - loss: 0.6083 - mean_absolute_error: 0.6083 Epoch 47/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6301 - mean_absolute_error: 0.6250 Epoch 48/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6446 - mean_absolute_error: 0.6327 Epoch 49/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.6340 - mean_absolute_error: 0.6259 Epoch 50/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6071 - mean_absolute_error: 0.6070 Epoch 51/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.6283 - mean_absolute_error: 0.6224 Epoch 52/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6469 - mean_absolute_error: 0.6298 Epoch 53/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.6364 - mean_absolute_error: 0.6231 Epoch 54/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.6324 - mean_absolute_error: 0.6284 Epoch 55/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6039 - mean_absolute_error: 0.6078 Epoch 56/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.6148 - mean_absolute_error: 0.6135 Epoch 57/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.6085 - mean_absolute_error: 0.6128 Epoch 58/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6289 - mean_absolute_error: 0.6224 Epoch 59/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6131 - mean_absolute_error: 0.6157 Epoch 60/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6043 - mean_absolute_error: 0.6040 Epoch 61/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.5838 - mean_absolute_error: 0.5992 Epoch 62/100 1043/1043 [==============================] - 0s 65us/step - loss: 0.6040 - mean_absolute_error: 0.6100 Epoch 63/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.6041 - mean_absolute_error: 0.6097 Epoch 64/100 1043/1043 [==============================] - 0s 74us/step - loss: 0.6120 - mean_absolute_error: 0.6113 Epoch 65/100 1043/1043 [==============================] - 0s 65us/step - loss: 0.6036 - mean_absolute_error: 0.6084 Epoch 66/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5903 - mean_absolute_error: 0.6042 Epoch 67/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.6037 - mean_absolute_error: 0.6058 Epoch 68/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.6031 - mean_absolute_error: 0.6098 Epoch 69/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.6220 - mean_absolute_error: 0.6136 Epoch 70/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6183 - mean_absolute_error: 0.6165 Epoch 71/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.5952 - mean_absolute_error: 0.6034 Epoch 72/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.6159 - mean_absolute_error: 0.6142 Epoch 73/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6087 - mean_absolute_error: 0.6080 Epoch 74/100 1043/1043 [==============================] - 0s 73us/step - loss: 0.5886 - mean_absolute_error: 0.5932 Epoch 75/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5954 - mean_absolute_error: 0.6029 Epoch 76/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5933 - mean_absolute_error: 0.6002 Epoch 77/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.5839 - mean_absolute_error: 0.6022 Epoch 78/100 1043/1043 [==============================] - 0s 69us/step - loss: 0.5753 - mean_absolute_error: 0.5890 Epoch 79/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5737 - mean_absolute_error: 0.5850 Epoch 80/100 1043/1043 [==============================] - 0s 67us/step - loss: 0.5820 - mean_absolute_error: 0.5939 Epoch 81/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.6174 - mean_absolute_error: 0.6145 Epoch 82/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5758 - mean_absolute_error: 0.5913 Epoch 83/100 1043/1043 [==============================] - 0s 65us/step - loss: 0.5679 - mean_absolute_error: 0.5874 Epoch 84/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5773 - mean_absolute_error: 0.6004 Epoch 85/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5761 - mean_absolute_error: 0.5887 Epoch 86/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.6123 - mean_absolute_error: 0.6115 Epoch 87/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5876 - mean_absolute_error: 0.5959 Epoch 88/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5828 - mean_absolute_error: 0.5892 Epoch 89/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5974 - mean_absolute_error: 0.5989 Epoch 90/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5713 - mean_absolute_error: 0.5944 Epoch 91/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5969 - mean_absolute_error: 0.5975 Epoch 92/100 1043/1043 [==============================] - 0s 78us/step - loss: 0.5962 - mean_absolute_error: 0.6025 Epoch 93/100 1043/1043 [==============================] - 0s 72us/step - loss: 0.5904 - mean_absolute_error: 0.6017 Epoch 94/100 1043/1043 [==============================] - 0s 70us/step - loss: 0.5861 - mean_absolute_error: 0.5995 Epoch 95/100 1043/1043 [==============================] - 0s 65us/step - loss: 0.5957 - mean_absolute_error: 0.6029 Epoch 96/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5732 - mean_absolute_error: 0.5929 Epoch 97/100 1043/1043 [==============================] - 0s 68us/step - loss: 0.5948 - mean_absolute_error: 0.6004 Epoch 98/100 1043/1043 [==============================] - 0s 71us/step - loss: 0.5779 - mean_absolute_error: 0.5948 Epoch 99/100 1043/1043 [==============================] - 0s 66us/step - loss: 0.5921 - mean_absolute_error: 0.5957 Epoch 100/100 1043/1043 [==============================] - 0s 76us/step - loss: 0.5800 - mean_absolute_error: 0.5942
train0 = df0[0:891].copy()
test0 = df0[891:].copy()
df0_cols = len(df0.columns)
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(df0_cols,)))
model.add(Dropout(0.5))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['acc'])
epochs=300
hist = model.fit(train0, train.Survived, epochs=epochs, batch_size=5)
pred = model.predict(test0)
Epoch 1/300 891/891 [==============================] - 3s 4ms/step - loss: 0.6436 - acc: 0.6667 Epoch 2/300 891/891 [==============================] - 0s 421us/step - loss: 0.5247 - acc: 0.7464 Epoch 3/300 891/891 [==============================] - 0s 426us/step - loss: 0.5265 - acc: 0.7576 Epoch 4/300 891/891 [==============================] - 0s 417us/step - loss: 0.5045 - acc: 0.7901 Epoch 5/300 891/891 [==============================] - 0s 420us/step - loss: 0.4819 - acc: 0.7935 Epoch 6/300 891/891 [==============================] - 0s 434us/step - loss: 0.4564 - acc: 0.8081 Epoch 7/300 891/891 [==============================] - 0s 416us/step - loss: 0.4491 - acc: 0.8171 Epoch 8/300 891/891 [==============================] - 0s 490us/step - loss: 0.4387 - acc: 0.8215 Epoch 9/300 891/891 [==============================] - 0s 491us/step - loss: 0.4468 - acc: 0.8114 Epoch 10/300 891/891 [==============================] - 0s 418us/step - loss: 0.4530 - acc: 0.8249 Epoch 11/300 891/891 [==============================] - 0s 424us/step - loss: 0.4452 - acc: 0.8092 Epoch 12/300 891/891 [==============================] - 0s 414us/step - loss: 0.4237 - acc: 0.8361 Epoch 13/300 891/891 [==============================] - 0s 426us/step - loss: 0.4245 - acc: 0.8361 Epoch 14/300 891/891 [==============================] - 0s 427us/step - loss: 0.4375 - acc: 0.8283 Epoch 15/300 891/891 [==============================] - 0s 422us/step - loss: 0.4295 - acc: 0.8350 Epoch 16/300 891/891 [==============================] - 0s 427us/step - loss: 0.4209 - acc: 0.8294 Epoch 17/300 891/891 [==============================] - 0s 424us/step - loss: 0.4312 - acc: 0.8227 Epoch 18/300 891/891 [==============================] - 0s 495us/step - loss: 0.4225 - acc: 0.8283 Epoch 19/300 891/891 [==============================] - 0s 471us/step - loss: 0.4214 - acc: 0.8316 Epoch 20/300 891/891 [==============================] - 0s 536us/step - loss: 0.4205 - acc: 0.8305 Epoch 21/300 891/891 [==============================] - 0s 500us/step - loss: 0.3943 - acc: 0.8462 Epoch 22/300 891/891 [==============================] - 0s 498us/step - loss: 0.4137 - acc: 0.8418 Epoch 23/300 891/891 [==============================] - 0s 449us/step - loss: 0.3907 - acc: 0.8406 Epoch 24/300 891/891 [==============================] - 0s 460us/step - loss: 0.4048 - acc: 0.8361 Epoch 25/300 891/891 [==============================] - 0s 435us/step - loss: 0.4029 - acc: 0.8395 Epoch 26/300 891/891 [==============================] - 0s 452us/step - loss: 0.4138 - acc: 0.8328 Epoch 27/300 891/891 [==============================] - 0s 431us/step - loss: 0.4136 - acc: 0.8283 Epoch 28/300 891/891 [==============================] - 0s 452us/step - loss: 0.3948 - acc: 0.8418 Epoch 29/300 891/891 [==============================] - 0s 432us/step - loss: 0.4084 - acc: 0.8339 Epoch 30/300 891/891 [==============================] - 0s 532us/step - loss: 0.3949 - acc: 0.8440 Epoch 31/300 891/891 [==============================] - 0s 514us/step - loss: 0.3842 - acc: 0.8530 Epoch 32/300 891/891 [==============================] - 0s 505us/step - loss: 0.4046 - acc: 0.8373 Epoch 33/300 891/891 [==============================] - 0s 499us/step - loss: 0.3997 - acc: 0.8406 Epoch 34/300 891/891 [==============================] - 0s 501us/step - loss: 0.3888 - acc: 0.8597 Epoch 35/300 891/891 [==============================] - 0s 425us/step - loss: 0.3970 - acc: 0.8406 Epoch 36/300 891/891 [==============================] - 0s 423us/step - loss: 0.3822 - acc: 0.8418 Epoch 37/300 891/891 [==============================] - 0s 420us/step - loss: 0.3816 - acc: 0.8496 Epoch 38/300 891/891 [==============================] - 0s 428us/step - loss: 0.3950 - acc: 0.8496 Epoch 39/300 891/891 [==============================] - 0s 426us/step - loss: 0.3755 - acc: 0.8485 Epoch 40/300 891/891 [==============================] - 0s 432us/step - loss: 0.3896 - acc: 0.8328 Epoch 41/300 891/891 [==============================] - 0s 435us/step - loss: 0.3899 - acc: 0.8575 Epoch 42/300 891/891 [==============================] - 0s 424us/step - loss: 0.3710 - acc: 0.8519 Epoch 43/300 891/891 [==============================] - 0s 433us/step - loss: 0.3841 - acc: 0.8462 Epoch 44/300 891/891 [==============================] - 0s 427us/step - loss: 0.3828 - acc: 0.8418 Epoch 45/300 891/891 [==============================] - 0s 435us/step - loss: 0.3807 - acc: 0.8541 Epoch 46/300 891/891 [==============================] - 0s 421us/step - loss: 0.3768 - acc: 0.8519 Epoch 47/300 891/891 [==============================] - 0s 423us/step - loss: 0.3909 - acc: 0.8541 Epoch 48/300 891/891 [==============================] - 0s 437us/step - loss: 0.3795 - acc: 0.8541 Epoch 49/300 891/891 [==============================] - 0s 430us/step - loss: 0.3629 - acc: 0.8530 Epoch 50/300 891/891 [==============================] - 0s 425us/step - loss: 0.3775 - acc: 0.8485 Epoch 51/300 891/891 [==============================] - 0s 439us/step - loss: 0.3706 - acc: 0.8485 Epoch 52/300 891/891 [==============================] - 0s 426us/step - loss: 0.3812 - acc: 0.8485 Epoch 53/300 891/891 [==============================] - 0s 439us/step - loss: 0.3757 - acc: 0.8541 Epoch 54/300 891/891 [==============================] - 0s 433us/step - loss: 0.3697 - acc: 0.8440 Epoch 55/300 891/891 [==============================] - 0s 427us/step - loss: 0.3838 - acc: 0.8519 Epoch 56/300 891/891 [==============================] - 0s 435us/step - loss: 0.3723 - acc: 0.8485 Epoch 57/300 891/891 [==============================] - 0s 427us/step - loss: 0.3684 - acc: 0.8429 Epoch 58/300 891/891 [==============================] - 0s 434us/step - loss: 0.3633 - acc: 0.8586 Epoch 59/300 891/891 [==============================] - 0s 434us/step - loss: 0.3671 - acc: 0.8709 Epoch 60/300 891/891 [==============================] - 0s 416us/step - loss: 0.3753 - acc: 0.8462 Epoch 61/300 891/891 [==============================] - 0s 524us/step - loss: 0.3659 - acc: 0.8586 Epoch 62/300 891/891 [==============================] - 0s 489us/step - loss: 0.3600 - acc: 0.8620 Epoch 63/300 891/891 [==============================] - 0s 502us/step - loss: 0.3771 - acc: 0.8474 Epoch 64/300 891/891 [==============================] - 0s 469us/step - loss: 0.3642 - acc: 0.8620 Epoch 65/300 891/891 [==============================] - 0s 432us/step - loss: 0.3609 - acc: 0.8620 Epoch 66/300 891/891 [==============================] - 0s 437us/step - loss: 0.3674 - acc: 0.8586 Epoch 67/300 891/891 [==============================] - 0s 428us/step - loss: 0.3679 - acc: 0.8496 Epoch 68/300 891/891 [==============================] - 0s 440us/step - loss: 0.3458 - acc: 0.8620 Epoch 69/300 891/891 [==============================] - 0s 433us/step - loss: 0.3678 - acc: 0.8631 Epoch 70/300 891/891 [==============================] - 0s 430us/step - loss: 0.3675 - acc: 0.8642 Epoch 71/300 891/891 [==============================] - 0s 437us/step - loss: 0.3448 - acc: 0.8687 Epoch 72/300 891/891 [==============================] - 0s 427us/step - loss: 0.3574 - acc: 0.8530 Epoch 73/300 891/891 [==============================] - 0s 444us/step - loss: 0.3837 - acc: 0.8418 Epoch 74/300 891/891 [==============================] - 0s 429us/step - loss: 0.3468 - acc: 0.8575 Epoch 75/300 891/891 [==============================] - 0s 428us/step - loss: 0.3501 - acc: 0.8687 Epoch 76/300 891/891 [==============================] - 0s 441us/step - loss: 0.3681 - acc: 0.8507 Epoch 77/300 891/891 [==============================] - 0s 429us/step - loss: 0.3574 - acc: 0.8642 Epoch 78/300 891/891 [==============================] - 0s 429us/step - loss: 0.3550 - acc: 0.8440 Epoch 79/300 891/891 [==============================] - 0s 435us/step - loss: 0.3595 - acc: 0.8485 Epoch 80/300 891/891 [==============================] - 0s 427us/step - loss: 0.3530 - acc: 0.8664 Epoch 81/300 891/891 [==============================] - 0s 439us/step - loss: 0.3593 - acc: 0.8631 Epoch 82/300 891/891 [==============================] - 0s 434us/step - loss: 0.3634 - acc: 0.8608 Epoch 83/300 891/891 [==============================] - 0s 417us/step - loss: 0.3663 - acc: 0.8608 Epoch 84/300 891/891 [==============================] - 0s 412us/step - loss: 0.3556 - acc: 0.8530 Epoch 85/300 891/891 [==============================] - 0s 412us/step - loss: 0.3609 - acc: 0.8664 Epoch 86/300 891/891 [==============================] - 0s 401us/step - loss: 0.3446 - acc: 0.8575 Epoch 87/300 891/891 [==============================] - 0s 416us/step - loss: 0.3534 - acc: 0.8653 Epoch 88/300 891/891 [==============================] - 0s 403us/step - loss: 0.3654 - acc: 0.8653 Epoch 89/300 891/891 [==============================] - 0s 414us/step - loss: 0.3544 - acc: 0.8507 Epoch 90/300 891/891 [==============================] - 0s 415us/step - loss: 0.3628 - acc: 0.8597 Epoch 91/300 891/891 [==============================] - 0s 497us/step - loss: 0.3518 - acc: 0.8709 Epoch 92/300 891/891 [==============================] - 0s 531us/step - loss: 0.3498 - acc: 0.8507 Epoch 93/300 891/891 [==============================] - 0s 472us/step - loss: 0.3486 - acc: 0.8676 Epoch 94/300 891/891 [==============================] - 0s 465us/step - loss: 0.3629 - acc: 0.8698 Epoch 95/300 891/891 [==============================] - 0s 446us/step - loss: 0.3485 - acc: 0.8608 Epoch 96/300 891/891 [==============================] - 0s 454us/step - loss: 0.3397 - acc: 0.8620 Epoch 97/300 891/891 [==============================] - 0s 470us/step - loss: 0.3582 - acc: 0.8586 Epoch 98/300 891/891 [==============================] - 0s 427us/step - loss: 0.3405 - acc: 0.8687 Epoch 99/300 891/891 [==============================] - 0s 471us/step - loss: 0.3577 - acc: 0.8631 Epoch 100/300 891/891 [==============================] - 0s 460us/step - loss: 0.3600 - acc: 0.8575 Epoch 101/300 891/891 [==============================] - 0s 440us/step - loss: 0.3347 - acc: 0.8687 Epoch 102/300 891/891 [==============================] - 0s 417us/step - loss: 0.3495 - acc: 0.8620 Epoch 103/300 891/891 [==============================] - 0s 431us/step - loss: 0.3431 - acc: 0.8620 Epoch 104/300 891/891 [==============================] - 0s 437us/step - loss: 0.3571 - acc: 0.8552 Epoch 105/300 891/891 [==============================] - 0s 433us/step - loss: 0.3522 - acc: 0.8541 Epoch 106/300 891/891 [==============================] - 0s 463us/step - loss: 0.3393 - acc: 0.8631 Epoch 107/300 891/891 [==============================] - 0s 463us/step - loss: 0.3375 - acc: 0.8664 Epoch 108/300 891/891 [==============================] - 0s 428us/step - loss: 0.3444 - acc: 0.8563 Epoch 109/300 891/891 [==============================] - 0s 436us/step - loss: 0.3557 - acc: 0.8642 Epoch 110/300 891/891 [==============================] - 0s 426us/step - loss: 0.3549 - acc: 0.8620 Epoch 111/300 891/891 [==============================] - 0s 425us/step - loss: 0.3390 - acc: 0.8608 Epoch 112/300 891/891 [==============================] - 0s 425us/step - loss: 0.3396 - acc: 0.8698 Epoch 113/300 891/891 [==============================] - 0s 427us/step - loss: 0.3393 - acc: 0.8721 Epoch 114/300 891/891 [==============================] - 0s 436us/step - loss: 0.3435 - acc: 0.8732 Epoch 115/300 891/891 [==============================] - 0s 424us/step - loss: 0.3298 - acc: 0.8631 Epoch 116/300 891/891 [==============================] - 0s 425us/step - loss: 0.3393 - acc: 0.8608 Epoch 117/300 891/891 [==============================] - 0s 440us/step - loss: 0.3420 - acc: 0.8687 Epoch 118/300 891/891 [==============================] - 0s 429us/step - loss: 0.3459 - acc: 0.8552 Epoch 119/300 891/891 [==============================] - 0s 426us/step - loss: 0.3405 - acc: 0.8597 Epoch 120/300 891/891 [==============================] - 0s 440us/step - loss: 0.3313 - acc: 0.8653 Epoch 121/300 891/891 [==============================] - 0s 434us/step - loss: 0.3372 - acc: 0.8631 Epoch 122/300 891/891 [==============================] - 0s 436us/step - loss: 0.3351 - acc: 0.8664 Epoch 123/300 891/891 [==============================] - 0s 427us/step - loss: 0.3336 - acc: 0.8687 Epoch 124/300 891/891 [==============================] - 0s 494us/step - loss: 0.3475 - acc: 0.8608 Epoch 125/300 891/891 [==============================] - 0s 460us/step - loss: 0.3655 - acc: 0.8496 Epoch 126/300 891/891 [==============================] - 0s 445us/step - loss: 0.3315 - acc: 0.8631 Epoch 127/300 891/891 [==============================] - 0s 452us/step - loss: 0.3505 - acc: 0.8485 Epoch 128/300 891/891 [==============================] - 0s 472us/step - loss: 0.3415 - acc: 0.8676 Epoch 129/300 891/891 [==============================] - 0s 480us/step - loss: 0.3377 - acc: 0.8676 Epoch 130/300 891/891 [==============================] - 0s 456us/step - loss: 0.3396 - acc: 0.8709 Epoch 131/300 891/891 [==============================] - 0s 449us/step - loss: 0.3314 - acc: 0.8664 Epoch 132/300 891/891 [==============================] - 0s 501us/step - loss: 0.3402 - acc: 0.8676 Epoch 133/300 891/891 [==============================] - 0s 456us/step - loss: 0.3510 - acc: 0.8642 Epoch 134/300 891/891 [==============================] - 0s 441us/step - loss: 0.3251 - acc: 0.8687 Epoch 135/300 891/891 [==============================] - 0s 457us/step - loss: 0.3336 - acc: 0.8709 Epoch 136/300 891/891 [==============================] - 0s 447us/step - loss: 0.3341 - acc: 0.8698 Epoch 137/300 891/891 [==============================] - 0s 489us/step - loss: 0.3486 - acc: 0.8676 Epoch 138/300 891/891 [==============================] - 0s 469us/step - loss: 0.3343 - acc: 0.8676 Epoch 139/300 891/891 [==============================] - 0s 446us/step - loss: 0.3579 - acc: 0.8519 Epoch 140/300 891/891 [==============================] - 0s 450us/step - loss: 0.3465 - acc: 0.8597 Epoch 141/300 891/891 [==============================] - 0s 441us/step - loss: 0.3474 - acc: 0.8597 Epoch 142/300 891/891 [==============================] - 0s 442us/step - loss: 0.3450 - acc: 0.8620 Epoch 143/300 891/891 [==============================] - 0s 434us/step - loss: 0.3365 - acc: 0.8642 Epoch 144/300 891/891 [==============================] - 0s 443us/step - loss: 0.3432 - acc: 0.8541 Epoch 145/300 891/891 [==============================] - 0s 431us/step - loss: 0.3443 - acc: 0.8608 Epoch 146/300 891/891 [==============================] - 0s 432us/step - loss: 0.3475 - acc: 0.8608 Epoch 147/300 891/891 [==============================] - 0s 440us/step - loss: 0.3450 - acc: 0.8496 Epoch 148/300 891/891 [==============================] - 0s 434us/step - loss: 0.3211 - acc: 0.8754 Epoch 149/300 891/891 [==============================] - 0s 442us/step - loss: 0.3265 - acc: 0.8631 Epoch 150/300 891/891 [==============================] - 0s 444us/step - loss: 0.3364 - acc: 0.8676 Epoch 151/300 891/891 [==============================] - 0s 434us/step - loss: 0.3282 - acc: 0.8709 Epoch 152/300 891/891 [==============================] - 0s 442us/step - loss: 0.3392 - acc: 0.8608 Epoch 153/300 891/891 [==============================] - 0s 508us/step - loss: 0.3366 - acc: 0.8664 Epoch 154/300 891/891 [==============================] - 0s 475us/step - loss: 0.3372 - acc: 0.8664 Epoch 155/300 891/891 [==============================] - 0s 460us/step - loss: 0.3360 - acc: 0.8642 Epoch 156/300 891/891 [==============================] - 0s 437us/step - loss: 0.3407 - acc: 0.8620 Epoch 157/300 891/891 [==============================] - 0s 478us/step - loss: 0.3259 - acc: 0.8597 Epoch 158/300 891/891 [==============================] - 0s 485us/step - loss: 0.3415 - acc: 0.8586 Epoch 159/300 891/891 [==============================] - 0s 477us/step - loss: 0.3234 - acc: 0.8777 Epoch 160/300 891/891 [==============================] - 0s 444us/step - loss: 0.3458 - acc: 0.8653 Epoch 161/300 891/891 [==============================] - 0s 458us/step - loss: 0.3378 - acc: 0.8664 Epoch 162/300 891/891 [==============================] - 0s 459us/step - loss: 0.3352 - acc: 0.8687 Epoch 163/300 891/891 [==============================] - 0s 436us/step - loss: 0.3363 - acc: 0.8563 Epoch 164/300 891/891 [==============================] - 0s 476us/step - loss: 0.3364 - acc: 0.8721 Epoch 165/300 891/891 [==============================] - 0s 471us/step - loss: 0.3443 - acc: 0.8597 Epoch 166/300 891/891 [==============================] - 0s 448us/step - loss: 0.3240 - acc: 0.8721 Epoch 167/300 891/891 [==============================] - 0s 462us/step - loss: 0.3314 - acc: 0.8608 Epoch 168/300 891/891 [==============================] - 0s 456us/step - loss: 0.3423 - acc: 0.8586 Epoch 169/300 891/891 [==============================] - 0s 465us/step - loss: 0.3447 - acc: 0.8597 Epoch 170/300 891/891 [==============================] - 0s 458us/step - loss: 0.3500 - acc: 0.8698 Epoch 171/300 891/891 [==============================] - 0s 464us/step - loss: 0.3368 - acc: 0.8530 Epoch 172/300 891/891 [==============================] - 0s 419us/step - loss: 0.3378 - acc: 0.8563 Epoch 173/300 891/891 [==============================] - 0s 455us/step - loss: 0.3408 - acc: 0.8631 Epoch 174/300 891/891 [==============================] - 0s 429us/step - loss: 0.3328 - acc: 0.8676 Epoch 175/300 891/891 [==============================] - 0s 467us/step - loss: 0.3388 - acc: 0.8754 Epoch 176/300 891/891 [==============================] - 0s 446us/step - loss: 0.3400 - acc: 0.8687 Epoch 177/300 891/891 [==============================] - 0s 433us/step - loss: 0.3329 - acc: 0.8642 Epoch 178/300 891/891 [==============================] - 0s 461us/step - loss: 0.3285 - acc: 0.8754 Epoch 179/300 891/891 [==============================] - 0s 465us/step - loss: 0.3381 - acc: 0.8620 Epoch 180/300 891/891 [==============================] - 0s 447us/step - loss: 0.3270 - acc: 0.8664 Epoch 181/300 891/891 [==============================] - 0s 433us/step - loss: 0.3294 - acc: 0.8687 Epoch 182/300 891/891 [==============================] - 0s 426us/step - loss: 0.3376 - acc: 0.8586 Epoch 183/300 891/891 [==============================] - 0s 423us/step - loss: 0.3236 - acc: 0.8664 Epoch 184/300 891/891 [==============================] - 0s 475us/step - loss: 0.3342 - acc: 0.8687 Epoch 185/300 891/891 [==============================] - 0s 433us/step - loss: 0.3374 - acc: 0.8687 Epoch 186/300 891/891 [==============================] - 0s 482us/step - loss: 0.3404 - acc: 0.8631 Epoch 187/300 891/891 [==============================] - 0s 459us/step - loss: 0.3302 - acc: 0.8642 Epoch 188/300 891/891 [==============================] - 0s 436us/step - loss: 0.3205 - acc: 0.8732 Epoch 189/300 891/891 [==============================] - 0s 469us/step - loss: 0.3344 - acc: 0.8642 Epoch 190/300 891/891 [==============================] - 0s 443us/step - loss: 0.3246 - acc: 0.8765 Epoch 191/300 891/891 [==============================] - 0s 457us/step - loss: 0.3321 - acc: 0.8597 Epoch 192/300 891/891 [==============================] - 0s 465us/step - loss: 0.3268 - acc: 0.8496 Epoch 193/300 891/891 [==============================] - 0s 463us/step - loss: 0.3245 - acc: 0.8687 Epoch 194/300 891/891 [==============================] - 0s 474us/step - loss: 0.3178 - acc: 0.8732 Epoch 195/300 891/891 [==============================] - 0s 459us/step - loss: 0.3221 - acc: 0.8721 Epoch 196/300 891/891 [==============================] - 0s 470us/step - loss: 0.3183 - acc: 0.8754 Epoch 197/300 891/891 [==============================] - 0s 438us/step - loss: 0.3198 - acc: 0.8732 Epoch 198/300 891/891 [==============================] - 0s 481us/step - loss: 0.3371 - acc: 0.8530 Epoch 199/300 891/891 [==============================] - 0s 472us/step - loss: 0.3303 - acc: 0.8687 Epoch 200/300 891/891 [==============================] - 0s 431us/step - loss: 0.3264 - acc: 0.8754 Epoch 201/300 891/891 [==============================] - 0s 485us/step - loss: 0.3396 - acc: 0.8586 Epoch 202/300 891/891 [==============================] - 0s 459us/step - loss: 0.3085 - acc: 0.8799 Epoch 203/300 891/891 [==============================] - 0s 448us/step - loss: 0.3243 - acc: 0.8597 Epoch 204/300 891/891 [==============================] - 0s 464us/step - loss: 0.3154 - acc: 0.8687 Epoch 205/300 891/891 [==============================] - 0s 478us/step - loss: 0.3088 - acc: 0.8743 Epoch 206/300 891/891 [==============================] - 0s 474us/step - loss: 0.3352 - acc: 0.8541 Epoch 207/300 891/891 [==============================] - 0s 430us/step - loss: 0.3234 - acc: 0.8732 Epoch 208/300 891/891 [==============================] - 0s 474us/step - loss: 0.3375 - acc: 0.8676 Epoch 209/300 891/891 [==============================] - 0s 459us/step - loss: 0.3294 - acc: 0.8552 Epoch 210/300 891/891 [==============================] - 0s 465us/step - loss: 0.3402 - acc: 0.8597 Epoch 211/300 891/891 [==============================] - 0s 460us/step - loss: 0.3208 - acc: 0.8709 Epoch 212/300 891/891 [==============================] - 0s 481us/step - loss: 0.3168 - acc: 0.8676 Epoch 213/300 891/891 [==============================] - 0s 483us/step - loss: 0.3257 - acc: 0.8620 Epoch 214/300 891/891 [==============================] - 0s 452us/step - loss: 0.3171 - acc: 0.8687 Epoch 215/300 891/891 [==============================] - 0s 484us/step - loss: 0.3194 - acc: 0.8664 Epoch 216/300 891/891 [==============================] - 0s 465us/step - loss: 0.3239 - acc: 0.8676 Epoch 217/300 891/891 [==============================] - 0s 441us/step - loss: 0.3311 - acc: 0.8642 Epoch 218/300 891/891 [==============================] - 0s 469us/step - loss: 0.3095 - acc: 0.8765 Epoch 219/300 891/891 [==============================] - 0s 438us/step - loss: 0.3136 - acc: 0.8721 Epoch 220/300 891/891 [==============================] - 0s 476us/step - loss: 0.3162 - acc: 0.8799 Epoch 221/300 891/891 [==============================] - 0s 434us/step - loss: 0.3337 - acc: 0.8552 Epoch 222/300 891/891 [==============================] - 0s 480us/step - loss: 0.3153 - acc: 0.8799 Epoch 223/300 891/891 [==============================] - 0s 469us/step - loss: 0.3255 - acc: 0.8721 Epoch 224/300 891/891 [==============================] - 0s 473us/step - loss: 0.3099 - acc: 0.8754 Epoch 225/300 891/891 [==============================] - 0s 473us/step - loss: 0.3230 - acc: 0.8732 Epoch 226/300 891/891 [==============================] - 0s 460us/step - loss: 0.3162 - acc: 0.8754 Epoch 227/300 891/891 [==============================] - 0s 460us/step - loss: 0.3282 - acc: 0.8664 Epoch 228/300 891/891 [==============================] - 0s 473us/step - loss: 0.3278 - acc: 0.8676 Epoch 229/300 891/891 [==============================] - 0s 435us/step - loss: 0.3270 - acc: 0.8732 Epoch 230/300 891/891 [==============================] - 0s 471us/step - loss: 0.3320 - acc: 0.8664 Epoch 231/300 891/891 [==============================] - 0s 473us/step - loss: 0.3233 - acc: 0.8642 Epoch 232/300 891/891 [==============================] - 0s 472us/step - loss: 0.3389 - acc: 0.8608 Epoch 233/300 891/891 [==============================] - 0s 433us/step - loss: 0.3121 - acc: 0.8822 Epoch 234/300 891/891 [==============================] - 0s 470us/step - loss: 0.3227 - acc: 0.8754 Epoch 235/300 891/891 [==============================] - 0s 487us/step - loss: 0.3332 - acc: 0.8620 Epoch 236/300 891/891 [==============================] - 0s 436us/step - loss: 0.3363 - acc: 0.8698 Epoch 237/300 891/891 [==============================] - 0s 473us/step - loss: 0.3169 - acc: 0.8687 Epoch 238/300 891/891 [==============================] - 0s 473us/step - loss: 0.3261 - acc: 0.8721 Epoch 239/300 891/891 [==============================] - 0s 464us/step - loss: 0.3182 - acc: 0.8709 Epoch 240/300 891/891 [==============================] - 0s 472us/step - loss: 0.3122 - acc: 0.8765 Epoch 241/300 891/891 [==============================] - 0s 462us/step - loss: 0.3290 - acc: 0.8597 Epoch 242/300 891/891 [==============================] - 0s 479us/step - loss: 0.3188 - acc: 0.8653 Epoch 243/300 891/891 [==============================] - 0s 465us/step - loss: 0.3368 - acc: 0.8664 Epoch 244/300 891/891 [==============================] - 0s 435us/step - loss: 0.3117 - acc: 0.8866 Epoch 245/300 891/891 [==============================] - 0s 435us/step - loss: 0.3180 - acc: 0.8743 Epoch 246/300 891/891 [==============================] - 0s 430us/step - loss: 0.3187 - acc: 0.8687 Epoch 247/300 891/891 [==============================] - 0s 425us/step - loss: 0.3135 - acc: 0.8765 Epoch 248/300 891/891 [==============================] - 0s 407us/step - loss: 0.3281 - acc: 0.8642 Epoch 249/300 891/891 [==============================] - 0s 411us/step - loss: 0.3199 - acc: 0.8732 Epoch 250/300 891/891 [==============================] - 0s 417us/step - loss: 0.3251 - acc: 0.8575 Epoch 251/300 891/891 [==============================] - 0s 408us/step - loss: 0.3311 - acc: 0.8620 Epoch 252/300 891/891 [==============================] - 0s 416us/step - loss: 0.3257 - acc: 0.8709 Epoch 253/300 891/891 [==============================] - 0s 425us/step - loss: 0.3301 - acc: 0.8631 Epoch 254/300 891/891 [==============================] - 0s 404us/step - loss: 0.3456 - acc: 0.8586 Epoch 255/300 891/891 [==============================] - 0s 418us/step - loss: 0.3187 - acc: 0.8698 Epoch 256/300 891/891 [==============================] - 0s 494us/step - loss: 0.3101 - acc: 0.8754 Epoch 257/300 891/891 [==============================] - 0s 462us/step - loss: 0.3315 - acc: 0.8575 Epoch 258/300 891/891 [==============================] - 0s 433us/step - loss: 0.3082 - acc: 0.8777 Epoch 259/300 891/891 [==============================] - 0s 459us/step - loss: 0.3153 - acc: 0.8664 Epoch 260/300 891/891 [==============================] - 0s 472us/step - loss: 0.3260 - acc: 0.8653 Epoch 261/300 891/891 [==============================] - 0s 428us/step - loss: 0.3165 - acc: 0.8698 Epoch 262/300 891/891 [==============================] - 0s 490us/step - loss: 0.3186 - acc: 0.8653 Epoch 263/300 891/891 [==============================] - 0s 434us/step - loss: 0.3210 - acc: 0.8687 Epoch 264/300 891/891 [==============================] - 0s 481us/step - loss: 0.3164 - acc: 0.8732 Epoch 265/300 891/891 [==============================] - 0s 441us/step - loss: 0.3193 - acc: 0.8631 Epoch 266/300 891/891 [==============================] - 0s 478us/step - loss: 0.3302 - acc: 0.8552 Epoch 267/300 891/891 [==============================] - 0s 462us/step - loss: 0.3163 - acc: 0.8765 Epoch 268/300 891/891 [==============================] - 0s 470us/step - loss: 0.3207 - acc: 0.8822 Epoch 269/300 891/891 [==============================] - 0s 460us/step - loss: 0.3256 - acc: 0.8687 Epoch 270/300 891/891 [==============================] - 0s 462us/step - loss: 0.3140 - acc: 0.8754 Epoch 271/300 891/891 [==============================] - 0s 430us/step - loss: 0.3178 - acc: 0.8754 Epoch 272/300 891/891 [==============================] - 0s 501us/step - loss: 0.3304 - acc: 0.8664 Epoch 273/300 891/891 [==============================] - 0s 463us/step - loss: 0.3251 - acc: 0.8777 Epoch 274/300 891/891 [==============================] - 0s 458us/step - loss: 0.3159 - acc: 0.8743 Epoch 275/300 891/891 [==============================] - 0s 470us/step - loss: 0.3095 - acc: 0.8810 Epoch 276/300 891/891 [==============================] - 0s 471us/step - loss: 0.3104 - acc: 0.8732 Epoch 277/300 891/891 [==============================] - 0s 490us/step - loss: 0.3298 - acc: 0.8698 Epoch 278/300 891/891 [==============================] - 0s 446us/step - loss: 0.3264 - acc: 0.8754 Epoch 279/300 891/891 [==============================] - 0s 487us/step - loss: 0.3139 - acc: 0.8799 Epoch 280/300 891/891 [==============================] - 0s 470us/step - loss: 0.3140 - acc: 0.8765 Epoch 281/300 891/891 [==============================] - 0s 485us/step - loss: 0.3164 - acc: 0.8743 Epoch 282/300 891/891 [==============================] - 0s 481us/step - loss: 0.3134 - acc: 0.8754 Epoch 283/300 891/891 [==============================] - 0s 433us/step - loss: 0.3225 - acc: 0.8777 Epoch 284/300 891/891 [==============================] - 0s 434us/step - loss: 0.3098 - acc: 0.8732 Epoch 285/300 891/891 [==============================] - 0s 431us/step - loss: 0.3222 - acc: 0.8698 Epoch 286/300 891/891 [==============================] - 0s 433us/step - loss: 0.3269 - acc: 0.8676 Epoch 287/300 891/891 [==============================] - 0s 443us/step - loss: 0.3188 - acc: 0.8664 Epoch 288/300 891/891 [==============================] - 0s 482us/step - loss: 0.3190 - acc: 0.8754 Epoch 289/300 891/891 [==============================] - 0s 472us/step - loss: 0.3009 - acc: 0.8777 Epoch 290/300 891/891 [==============================] - 0s 458us/step - loss: 0.3266 - acc: 0.8698 Epoch 291/300 891/891 [==============================] - 0s 459us/step - loss: 0.3266 - acc: 0.8721 Epoch 292/300 891/891 [==============================] - 0s 455us/step - loss: 0.3143 - acc: 0.8698 Epoch 293/300 891/891 [==============================] - 0s 475us/step - loss: 0.3299 - acc: 0.8653 Epoch 294/300 891/891 [==============================] - 0s 460us/step - loss: 0.3165 - acc: 0.8698 Epoch 295/300 891/891 [==============================] - 0s 482us/step - loss: 0.3148 - acc: 0.8765 Epoch 296/300 891/891 [==============================] - 0s 436us/step - loss: 0.3335 - acc: 0.8620 Epoch 297/300 891/891 [==============================] - 0s 482us/step - loss: 0.3139 - acc: 0.8732 Epoch 298/300 891/891 [==============================] - 0s 458us/step - loss: 0.3345 - acc: 0.8709 Epoch 299/300 891/891 [==============================] - 0s 458us/step - loss: 0.3225 - acc: 0.8687 Epoch 300/300 891/891 [==============================] - 0s 465us/step - loss: 0.3049 - acc: 0.8822
# print(model.metrics_names)
plt.plot(hist.history['acc'], 'b-', label='acc' )
plt.plot(hist.history['loss'], 'r-', label='loss' )
plt.xlabel('epochs')
plt.legend()
plt.show()
result = pred.argmax(axis=1)
submission = pd.DataFrame({'PassengerId': test.index, 'Survived': result})
submission.to_csv('titanic/submission.csv', index=False)