/
Kaggle Kernel.py
311 lines (289 loc) · 10.8 KB
/
Kaggle Kernel.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
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
#Machine Learning Dig
# Imports
# pandas
import pandas as pd
from pandas import Series,DataFrame
# numpy, matplotlib, seaborn
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('whitegrid')
%matplotlib inline
# machine learning
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
# get titanic & test csv files as a DataFrame
titanic_df = pd.read_csv("../input/train.csv", dtype={"Age": np.float64}, )
test_df = pd.read_csv("../input/test.csv", dtype={"Age": np.float64}, )
# preview the data
titanic_df.head()
titanic_df.info()
print("----------------------------")
test_df.info()
# drop unnecessary columns, these columns won't be useful in analysis and prediction
titanic_df = titanic_df.drop(['PassengerId','Name','Ticket'], axis=1)
test_df = test_df.drop(['Name','Ticket'], axis=1)
# Embarked
# only in titanic_df, fill the two missing values with the most occurred value, which is "S".
titanic_df["Embarked"] = titanic_df["Embarked"].fillna("S")
# plot
sns.factorplot('Embarked','Survived', data=titanic_df,size=4,aspect=3)
fig, (axis1,axis2,axis3) = plt.subplots(1,3,figsize=(15,5))
# sns.factorplot('Embarked',data=titanic_df,kind='count',order=['S','C','Q'],ax=axis1)
# sns.factorplot('Survived',hue="Embarked",data=titanic_df,kind='count',order=[1,0],ax=axis2)
sns.countplot(x='Embarked', data=titanic_df, ax=axis1)
sns.countplot(x='Survived', hue="Embarked", data=titanic_df, order=[1,0], ax=axis2)
# group by embarked, and get the mean for survived passengers for each value in Embarked
embark_perc = titanic_df[["Embarked", "Survived"]].groupby(['Embarked'],as_index=False).mean()
sns.barplot(x='Embarked', y='Survived', data=embark_perc,order=['S','C','Q'],ax=axis3)
# Either to consider Embarked column in predictions,
# and remove "S" dummy variable,
# and leave "C" & "Q", since they seem to have a good rate for Survival.
# OR, don't create dummy variables for Embarked column, just drop it,
# because logically, Embarked doesn't seem to be useful in prediction.
embark_dummies_titanic = pd.get_dummies(titanic_df['Embarked'])
embark_dummies_titanic.drop(['S'], axis=1, inplace=True)
embark_dummies_test = pd.get_dummies(test_df['Embarked'])
embark_dummies_test.drop(['S'], axis=1, inplace=True)
titanic_df = titanic_df.join(embark_dummies_titanic)
test_df = test_df.join(embark_dummies_test)
titanic_df.drop(['Embarked'], axis=1,inplace=True)
test_df.drop(['Embarked'], axis=1,inplace=True)
# Fare
# only for test_df, since there is a missing "Fare" values
test_df["Fare"].fillna(test_df["Fare"].median(), inplace=True)
# convert from float to int
titanic_df['Fare'] = titanic_df['Fare'].astype(int)
test_df['Fare'] = test_df['Fare'].astype(int)
# get fare for survived & didn't survive passengers
fare_not_survived = titanic_df["Fare"][titanic_df["Survived"] == 0]
fare_survived = titanic_df["Fare"][titanic_df["Survived"] == 1]
# get average and std for fare of survived/not survived passengers
avgerage_fare = DataFrame([fare_not_survived.mean(), fare_survived.mean()])
std_fare = DataFrame([fare_not_survived.std(), fare_survived.std()])
# plot
titanic_df['Fare'].plot(kind='hist', figsize=(15,3),bins=100, xlim=(0,50))
avgerage_fare.index.names = std_fare.index.names = ["Survived"]
avgerage_fare.plot(yerr=std_fare,kind='bar',legend=False)
# Age
fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,4))
axis1.set_title('Original Age values - Titanic')
axis2.set_title('New Age values - Titanic')
# axis3.set_title('Original Age values - Test')
# axis4.set_title('New Age values - Test')
# get average, std, and number of NaN values in titanic_df
average_age_titanic = titanic_df["Age"].mean()
std_age_titanic = titanic_df["Age"].std()
count_nan_age_titanic = titanic_df["Age"].isnull().sum()
# get average, std, and number of NaN values in test_df
average_age_test = test_df["Age"].mean()
std_age_test = test_df["Age"].std()
count_nan_age_test = test_df["Age"].isnull().sum()
# generate random numbers between (mean - std) & (mean + std)
rand_1 = np.random.randint(average_age_titanic - std_age_titanic, average_age_titanic + std_age_titanic, size = count_nan_age_titanic)
rand_2 = np.random.randint(average_age_test - std_age_test, average_age_test + std_age_test, size = count_nan_age_test)
# plot original Age values
# NOTE: drop all null values, and convert to int
titanic_df['Age'].dropna().astype(int).hist(bins=70, ax=axis1)
# test_df['Age'].dropna().astype(int).hist(bins=70, ax=axis1)
# fill NaN values in Age column with random values generated
titanic_df["Age"][np.isnan(titanic_df["Age"])] = rand_1
test_df["Age"][np.isnan(test_df["Age"])] = rand_2
# convert from float to int
titanic_df['Age'] = titanic_df['Age'].astype(int)
test_df['Age'] = test_df['Age'].astype(int)
# plot new Age Values
titanic_df['Age'].hist(bins=70, ax=axis2)
# test_df['Age'].hist(bins=70, ax=axis4)
# .... continue with plot Age column
# peaks for survived/not survived passengers by their age
facet = sns.FacetGrid(titanic_df, hue="Survived",aspect=4)
facet.map(sns.kdeplot,'Age',shade= True)
facet.set(xlim=(0, titanic_df['Age'].max()))
facet.add_legend()
# average survived passengers by age
fig, axis1 = plt.subplots(1,1,figsize=(18,4))
average_age = titanic_df[["Age", "Survived"]].groupby(['Age'],as_index=False).mean()
sns.barplot(x='Age', y='Survived', data=average_age)
# Cabin
# It has a lot of NaN values, so it won't cause a remarkable impact on prediction
titanic_df.drop("Cabin",axis=1,inplace=True)
test_df.drop("Cabin",axis=1,inplace=True)
# Family
# Instead of having two columns Parch & SibSp,
# we can have only one column represent if the passenger had any family member aboard or not,
# Meaning, if having any family member(whether parent, brother, ...etc) will increase chances of Survival or not.
titanic_df['Family'] = titanic_df["Parch"] + titanic_df["SibSp"]
titanic_df['Family'].loc[titanic_df['Family'] > 0] = 1
titanic_df['Family'].loc[titanic_df['Family'] == 0] = 0
test_df['Family'] = test_df["Parch"] + test_df["SibSp"]
test_df['Family'].loc[test_df['Family'] > 0] = 1
test_df['Family'].loc[test_df['Family'] == 0] = 0
# drop Parch & SibSp
titanic_df = titanic_df.drop(['SibSp','Parch'], axis=1)
test_df = test_df.drop(['SibSp','Parch'], axis=1)
# plot
fig, (axis1,axis2) = plt.subplots(1,2,sharex=True,figsize=(10,5))
# sns.factorplot('Family',data=titanic_df,kind='count',ax=axis1)
sns.countplot(x='Family', data=titanic_df, order=[1,0], ax=axis1)
# average of survived for those who had/didn't have any family member
family_perc = titanic_df[["Family", "Survived"]].groupby(['Family'],as_index=False).mean()
sns.barplot(x='Family', y='Survived', data=family_perc, order=[1,0], ax=axis2)
axis1.set_xticklabels(["With Family","Alone"], rotation=0)
# Sex
# As we see, children(age < ~16) on aboard seem to have a high chances for Survival.
# So, we can classify passengers as males, females, and child
def get_person(passenger):
age,sex = passenger
return 'child' if age < 16 else sex
titanic_df['Person'] = titanic_df[['Age','Sex']].apply(get_person,axis=1)
test_df['Person'] = test_df[['Age','Sex']].apply(get_person,axis=1)
# No need to use Sex column since we created Person column
titanic_df.drop(['Sex'],axis=1,inplace=True)
test_df.drop(['Sex'],axis=1,inplace=True)
# create dummy variables for Person column, & drop Male as it has the lowest average of survived passengers
person_dummies_titanic = pd.get_dummies(titanic_df['Person'])
person_dummies_titanic.columns = ['Child','Female','Male']
person_dummies_titanic.drop(['Male'], axis=1, inplace=True)
person_dummies_test = pd.get_dummies(test_df['Person'])
person_dummies_test.columns = ['Child','Female','Male']
person_dummies_test.drop(['Male'], axis=1, inplace=True)
titanic_df = titanic_df.join(person_dummies_titanic)
test_df = test_df.join(person_dummies_test)
fig, (axis1,axis2) = plt.subplots(1,2,figsize=(10,5))
# sns.factorplot('Person',data=titanic_df,kind='count',ax=axis1)
sns.countplot(x='Person', data=titanic_df, ax=axis1)
# average of survived for each Person(male, female, or child)
person_perc = titanic_df[["Person", "Survived"]].groupby(['Person'],as_index=False).mean()
sns.barplot(x='Person', y='Survived', data=person_perc, ax=axis2, order=['male','female','child'])
titanic_df.drop(['Person'],axis=1,inplace=True)
test_df.drop(['Person'],axis=1,inplace=True)
# Pclass
# sns.factorplot('Pclass',data=titanic_df,kind='count',order=[1,2,3])
sns.factorplot('Pclass','Survived',order=[1,2,3], data=titanic_df,size=5)
# create dummy variables for Pclass column, & drop 3rd class as it has the lowest average of survived passengers
pclass_dummies_titanic = pd.get_dummies(titanic_df['Pclass'])
pclass_dummies_titanic.columns = ['Class_1','Class_2','Class_3']
pclass_dummies_titanic.drop(['Class_3'], axis=1, inplace=True)
pclass_dummies_test = pd.get_dummies(test_df['Pclass'])
pclass_dummies_test.columns = ['Class_1','Class_2','Class_3']
pclass_dummies_test.drop(['Class_3'], axis=1, inplace=True)
titanic_df.drop(['Pclass'],axis=1,inplace=True)
test_df.drop(['Pclass'],axis=1,inplace=True)
titanic_df = titanic_df.join(pclass_dummies_titanic)
test_df = test_df.join(pclass_dummies_test)
# define training and testing sets
X_train = titanic_df.drop("Survived",axis=1)
Y_train = titanic_df["Survived"]
X_test = test_df.drop("PassengerId",axis=1).copy()
# Logistic Regression
logreg = LogisticRegression()
logreg.fit(X_train, Y_train)
Y_pred = logreg.predict(X_test)
logreg.score(X_train, Y_train)
# Support Vector Machines
# svc = SVC()
# svc.fit(X_train, Y_train)
# Y_pred = svc.predict(X_test)
# svc.score(X_train, Y_train)
# Random Forests
random_forest = RandomForestClassifier(n_estimators=100)
random_forest.fit(X_train, Y_train)
Y_pred = random_forest.predict(X_test)
random_forest.score(X_train, Y_train)
# knn = KNeighborsClassifier(n_neighbors = 3)
# knn.fit(X_train, Y_train)
# Y_pred = knn.predict(X_test)
# knn.score(X_train, Y_train)
# Gaussian Naive Bayes
# gaussian = GaussianNB()
# gaussian.fit(X_train, Y_train)
# Y_pred = gaussian.predict(X_test)
# gaussian.score(X_train, Y_train)
# get Correlation Coefficient for each feature using Logistic Regression
coeff_df = DataFrame(titanic_df.columns.delete(0))
coeff_df.columns = ['Features']
coeff_df["Coefficient Estimate"] = pd.Series(logreg.coef_[0])
# preview
coeff_df
submission = pd.DataFrame({
"PassengerId": test_df["PassengerId"],
"Survived": Y_pred
})
submission.to_csv('titanic.csv', index=False)