-
Notifications
You must be signed in to change notification settings - Fork 0
/
TitanicKaggle.py
150 lines (113 loc) · 5.06 KB
/
TitanicKaggle.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
import pandas as pd
import numpy as np
import random as rn
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib
import time
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
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier
# First attempt at machine learning problem
# Written in accordance with the tutorial on Kaggle
train_df = pd.read_csv("/Users/Nirzvi/Downloads/train.csv")
test_df = pd.read_csv("/Users/Nirzvi/Downloads/test.csv")
train_df = train_df.drop(['Ticket', 'Cabin'], axis=1)
test_df = test_df.drop(['Ticket', 'Cabin'], axis=1)
combine = [train_df, test_df]
for dataset in combine:
dataset['Title'] = dataset.Name.str.extract('([A-Za-z]+)\.', expand=False)
dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\
'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')
dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')
dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
dataset['Title'] = dataset['Title'].map({"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}).fillna(0)
train_df = train_df.drop(['Name', 'PassengerId'], axis=1)
test_df = test_df.drop(['Name'], axis=1)
combine = [train_df, test_df]
for dataset in combine:
dataset['Sex'] = dataset['Sex'].map({'female':1, 'male':0}).astype(int)
guess_ages = np.zeros((2,3))
for dataset in combine:
for i in range(0,2):
for j in range(0, 3):
guess_df = dataset[(dataset['Sex'] == i) & (dataset['Pclass'] == j+1)]['Age'].dropna()
age_guess = guess_df.median()
guess_ages[i][j] = int(age_guess / 0.5 + 0.5) * 0.5
for i in range(0,2):
for j in range(0, 3):
dataset.loc[(dataset.Age.isnull()) & (dataset['Sex'] == i) & (dataset['Pclass'] == j+1), 'Age'] = guess_ages[i,j]
dataset['Age'] = dataset['Age'].astype(int)
for dataset in combine:
dataset.loc[(dataset['Age'] <= 16), 'Age'] = 0
dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
dataset.loc[(dataset['Age'] > 64) & (dataset['Age'] <= 80), 'Age'] = 4
for dataset in combine:
dataset['FamilySize'] = dataset['Parch'] + dataset['SibSp'] + 1
dataset['IsAlone'] = 0
dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1
for dataset in combine:
freq_port = dataset['Embarked'].dropna().mode()[0]
dataset['Embarked'] = dataset['Embarked'].fillna(freq_port)
dataset['Embarked'] = dataset['Embarked'].map({'S':0, 'C':1, 'Q':2})
for dataset in combine:
dataset['Fare'] = dataset['Fare'].fillna(dataset['Fare'].dropna().median())
dataset.loc[(dataset['Fare'] <= 7.91), 'Fare'] = 0
dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare'] = 2
dataset.loc[(dataset['Fare'] > 31), 'Fare'] = 3
dataset['Fare'] = dataset['Fare'].astype(int)
for dataset in combine:
dataset['Age*Class'] = dataset.Age * dataset.Pclass
train_df = train_df.drop(['FamilySize', 'SibSp', 'Parch'], axis=1)
test_df = test_df.drop(['FamilySize', 'SibSp', 'Parch'], axis=1)
# print test_df.head(10)
X_train = train_df.drop('Survived', axis=1)
Y_train = train_df['Survived']
X_test = test_df.drop('PassengerId', axis=1)
logreg = LogisticRegression()
logreg.fit(X_train, Y_train)
Y_pred = logreg.predict(X_test)
acc_log = round(logreg.score(X_train, Y_train) * 100, 2)
print acc_log
coeff_df = pd.DataFrame(train_df.columns.delete(0))
coeff_df.columns = ['Feature']
coeff_df['Correlation'] = pd.Series(logreg.coef_[0])
print coeff_df.sort_values(by='Correlation', ascending=False)
svc = SVC()
svc.fit(X_train, Y_train)
Y_pred = svc.predict(X_test)
acc_svc = round(svc.score(X_train, Y_train) * 100, 2)
print acc_svc
knn = KNeighborsClassifier()
knn.fit(X_train, Y_train)
Y_pred = knn.predict(X_test)
acc_knn = round(knn.score(X_train, Y_train) * 100, 2)
print acc_knn
gnb = GaussianNB()
gnb.fit(X_train, Y_train)
Y_pred = gnb.predict(X_test)
acc_gaussian = round(gnb.score(X_train, Y_train) * 100, 2)
print acc_gaussian
percept = Perceptron()
percept.fit(X_train, Y_train)
Y_pred = percept.predict(X_test)
acc_percept = round(percept.score(X_train, Y_train) * 100, 2)
print acc_percept
# print pd.crosstab(train_df['Title'], train_df['Sex'])
#
# print train_df[['Title', 'Survived']].groupby('Title', as_index=False).mean().sort_values(by='Survived', ascending=False)
#
# grid = sns.FacetGrid(train_df, row='Survived')
# grid.map(plt.hist, 'Cabin', bins=20)
# grid.add_legend()
#
# plt.savefig("/Users/Nirzvi/Desktop/something.eps", dpi=100, format="eps", bbox_inches="tight")