1
2
3
# 多行输出
from IPython.core.interactiveshell import InteractiveShell 
InteractiveShell.ast_node_interactivity = 'all'  #默认为'last'

1
2
3
4
5
6
import numpy as np
import pandas as pd

train_data = pd.read_csv('//Volumes//windows//pythonstudy//titanic/train.csv')
test_data = pd.read_csv('//Volumes//windows//pythonstudy//titanic/test.csv')
train_data.head(5)

1
2
3
4
import os
for dirname, _, filenames in os.walk('//Volumes//windows//pythonstudy//titanic'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

1
os.getcwd()

1
2
3
4
# Show the survive rate of female
women = train_data.loc[train_data.Sex == 'female']['Survived']  # df.loc[val] selet a line or lines by index
rate_women = women.sum()/len(women)
rate_women

1
2
3
4
# Show the survive rate of male
men = train_data.loc[train_data.Sex == 'male']['Survived']  # df.loc[val] selet a line or lines by index
rate_men = men.sum()/len(men)
rate_men

1
2
3
4
5
6
7
# survive rate figured at every pclass
per_pclass_rate = []
for i in range(1,4):
    per_pclass = train_data.loc[train_data.Pclass == i]['Survived']  # df.loc[val] selet a line or lines by index
    per_pclass_rate_i = per_pclass.sum()/len(per_pclass)
    per_pclass_rate.append(per_pclass_rate_i)
per_pclass_rate

1
2
3
4
5
6
7
8
9
10
import matplotlib.pyplot as plt
fig, axes = plt.subplots(1,2)

data = pd.Series([rate_women, rate_men], index=['women','men'])
data.plot.bar(ax=axes[0],color='g',alpha=0.7)

data = pd.Series(per_pclass_rate, index=[1,2,3])
data.plot.bar(ax=axes[1],color='g',alpha=0.7)

1
2
3
4
5
6
7
# Pclass Sex SibSp Parch
y = train_data['Survived']
feature = ['Pclass', 'Sex', 'SibSp', 'Parch']
X = train_data[feature]  # one argument, which is a list
X_test = test_data[feature]
X
X_test

1
2
3
4
X = pd.get_dummies(X)
X_test = pd.get_dummies(X_test)
X
X_test

1
pd.get_dummies??

1
2
3
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier()
model.fit(X,y)

1
2
predictions = model.predict(X_test)
predictions

1
2
3
output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})
output.to_csv('./results/Titanic.csv', index=False)
print('My submission was successfully saved.')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
# Load in our libraries
import pandas as pd
import numpy as np
import re
import sklearn
import xgboost as xgb
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls

import warnings
warnings.filterwarnings('ignore')

# Going to use these 5 base models for the stacking
from sklearn.ensemble import (RandomForestClassifier, AdaBoostClassifier, 
                              GradientBoostingClassifier, ExtraTreesClassifier)
from sklearn.svm import SVC
from sklearn.model_selection import KFold

1
2
3
4
5
6
7
8
# Load in the train and test datasets
train = pd.read_csv('//Volumes//windows//pythonstudy//titanic/train.csv')
test = pd.read_csv('//Volumes//windows//pythonstudy//titanic/test.csv')

# Store our passenger ID for easy access
PassengerId = test['PassengerId']
PassengerId
train.head(3)

1
2
3
4
5
6
7
8
9
10
11
full_data = [train, test]  # a list joint train and test 

# Some features of my own that I have added in
# Gives the length of the name
train['Name_length'] = train['Name'].apply(len)
test['Name_length'] = test['Name'].apply(len)

# Feature that tells whether a passenger had a cabin on the Titanic
# type(NaN)=float,else is str
train['Has_Cabin'] = train["Cabin"].apply(lambda x: 0 if type(x) == float else 1)
test['Has_Cabin'] = test["Cabin"].apply(lambda x: 0 if type(x) == float else 1)

1
2
3
4
5
# Feature engineering steps taken from Sina
# Create new feature FamilySize as a combination of SibSp and Parch
# pandas can stright to creat a new col
for dataset in full_data:
    dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1

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
# Create new feature IsAlone from FamilySize
# row of FamilySize==1
for dataset in full_data:
    dataset['IsAlone'] = 0
    dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1
    
# Remove all NULLS in the Embarked column
for dataset in full_data:
    dataset['Embarked'] = dataset['Embarked'].fillna('S')
    
# Remove all NULLS in the Fare column and create a new feature CategoricalFare
for dataset in full_data:
    dataset['Fare'] = dataset['Fare'].fillna(train['Fare'].median())
train['CategoricalFare'] = pd.qcut(train['Fare'], 4)
# Create a New feature CategoricalAge
for dataset in full_data:
    age_avg = dataset['Age'].mean()
    age_std = dataset['Age'].std()
    age_null_count = dataset['Age'].isnull().sum()
    age_null_random_list = np.random.randint(age_avg - age_std, age_avg + age_std, size=age_null_count)
    dataset['Age'][np.isnan(dataset['Age'])] = age_null_random_list
    dataset['Age'] = dataset['Age'].astype(int)
train['CategoricalAge'] = pd.cut(train['Age'], 5)
# Define function to extract titles from passenger names
def get_title(name):
    title_search = re.search(' ([A-Za-z]+)\.', name)
    # If the title exists, extract and return it.
    if title_search:
        return title_search.group(1)
    return ""
# Create a new feature Title, containing the titles of passenger names
for dataset in full_data:
    dataset['Title'] = dataset['Name'].apply(get_title)
# Group all non-common titles into one single grouping "Rare"
for dataset in full_data:
    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('Ms', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')

for dataset in full_data:
    # Mapping Sex
    dataset['Sex'] = dataset['Sex'].map( {'female': 0, 'male': 1} ).astype(int)
    
    # Mapping titles
    title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}
    dataset['Title'] = dataset['Title'].map(title_mapping)
    dataset['Title'] = dataset['Title'].fillna(0)
    
    # Mapping Embarked
    dataset['Embarked'] = dataset['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)
    
    # Mapping Fare
    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)
    
    # Mapping Age
    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, 'Age'] = 4 ;