-
Notifications
You must be signed in to change notification settings - Fork 0
/
titanic.py
153 lines (107 loc) · 4.23 KB
/
titanic.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
#https://pinkwink.kr/1119?category=580892
raw_data = pd.read_excel('titanic.xls')
raw_data.info()
raw_data.describe()
f,ax=plt.subplots(1,2,figsize=(12,6))
raw_data['survived'].value_counts().plot.pie(explode=[0,0.1],autopct='%1.2f%%',ax=ax[0])
ax[0].set_title('Survived')
ax[0].set_ylabel('')
sns.countplot('survived',data=raw_data,ax=ax[1])
ax[1].set_title('Survived')
plt.show()
raw_data['age'].hist(bins=20,figsize=(18,8),grid=False)
raw_data.groupby('pclass').mean()
plt.figure(figsize=(10, 10))
sns.heatmap(raw_data.corr(), linewidths=0.01, square=True,
annot=True, cmap=plt.cm.viridis, linecolor="white")
plt.title('Correlation between features')
plt.show()
raw_data['age_cat'] = pd.cut(raw_data['age'], bins=[0, 10, 20, 50, 100],
include_lowest=True, labels=['baby', 'teenage', 'adult', 'old'])
plt.figure(figsize=[12,4])
plt.subplot(131)
sns.barplot('pclass', 'survived', data=raw_data)
plt.subplot(132)
sns.barplot('age_cat', 'survived', data=raw_data)
plt.subplot(133)
sns.barplot('sex', 'survived', data=raw_data)
plt.subplots_adjust(top=1, bottom=0.1, left=0.10, right=1, hspace=0.5, wspace=0.5)
plt.show()
f,ax = plt.subplots(figsize=(12,6))
g = sns.kdeplot(raw_data["age"][(raw_data["survived"] == 0) & (raw_data["age"].notnull())],
ax = ax, color="Blue", shade = True)
g = sns.kdeplot(raw_data["age"][(raw_data["survived"] == 1) & (raw_data["age"].notnull())],
ax =g, color="Green", shade= True)
g.set_xlabel("Age")
g.set_ylabel("Frequency")
g = g.legend(["Not Survived","Survived"])
f,ax=plt.subplots(1,2,figsize=(12,6))
sns.countplot('sex',data=raw_data, ax=ax[0])
ax[0].set_title('Count of Passengers by Sex')
sns.countplot('sex',hue='survived',data=raw_data, ax=ax[1])
ax[1].set_title('Sex:Survived vs Dead')
plt.show()
boat_survivors = raw_data[raw_data['boat'].notnull()]
f,ax=plt.subplots(1,2,figsize=(12,6))
boat_survivors['survived'].value_counts().plot.pie(explode=[0,0.1],autopct='%1.2f%%',ax=ax[0])
ax[0].set_title('Survived')
ax[0].set_ylabel('')
sns.countplot('survived',data=boat_survivors,ax=ax[1])
ax[1].set_title('Survived')
plt.show()
tmp = []
for each in raw_data['sex']:
if each == 'female':
tmp.append(1)
elif each == 'male':
tmp.append(0)
else:
tmp.append(np.nan)
raw_data['sex'] = tmp
raw_data['survived'] = raw_data['survived'].astype('float')
raw_data['pclass'] = raw_data['pclass'].astype('float')
raw_data['sex'] = raw_data['sex'].astype('float')
raw_data['sibsp'] = raw_data['sibsp'].astype('float')
raw_data['parch'] = raw_data['parch'].astype('float')
raw_data['fare'] = raw_data['fare'].astype('float')
raw_data = raw_data[raw_data['age'].notnull()]
raw_data = raw_data[raw_data['sibsp'].notnull()]
raw_data = raw_data[raw_data['parch'].notnull()]
raw_data = raw_data[raw_data['fare'].notnull()]
raw_data.info()
x_data = raw_data.values[:, [0,3,4,5,6,8]]
y_data = raw_data.values[:, [1]]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(x_data, y_data,
test_size=0.1, random_state=7)
import tensorflow as tf
import keras
from keras.models import Sequential
from keras.layers.core import Dense
np.random.seed(7)
print('tensorflow version : ', tf.__version__)
print('keras version : ', keras.__version__)
model = Sequential()
model.add(Dense(255, input_shape=(6,), activation='relu'))
model.add(Dense((1), activation='sigmoid'))
model.compile(loss='mse', optimizer='Adam', metrics=['accuracy'])
model.summary()
from IPython.display import SVG
from keras.utils.vis_utils import model_to_dot
SVG(model_to_dot(model, show_shapes=True).create(prog='dot', format='svg'))
hist = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=500)
plt.figure(figsize=(12,8))
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.plot(hist.history['acc'])
plt.plot(hist.history['val_acc'])
plt.legend(['loss','val_loss', 'acc','val_acc'])
plt.show()
dicaprio = np.array([3., 0., 19., 0., 0., 5.]).reshape(1,6)
winslet = np.array([1., 1., 17., 1., 2., 100.]).reshape(1,6)
model.predict(dicaprio)
model.predict(winslet)