Titanic Top 4% with ensemble modeling(1)

Introduction

Feature analysis

Feature engineering

Modeling

#라이브러리 호출
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

from collections import Counter

from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier, VotingClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import GridSearchCV, cross_val_score, StratifiedKFold, learning_curve

sns.set(style='white', context='notebook', palette='deep')

Load and Check data

load data

#load data
train = pd.read_csv('./input/train.csv')
test = pd.read_csv('./input/test.csv')
IDtest = test["PassengerId"]

Outlier detection

# Outlier detection 

def detect_outliers(df,n,features):
    """
    Takes a dataframe df of features and returns a list of the indices
    corresponding to the observations containing more than n outliers according
    to the Tukey method.
    """
    outlier_indices = []
    
    # iterate over features(columns)
    for col in features:
        # 1st quartile (25%)
        Q1 = np.percentile(df[col], 25)
        # 3rd quartile (75%)
        Q3 = np.percentile(df[col],75)
        # Interquartile range (IQR)
        IQR = Q3 - Q1
        
        # outlier step
        outlier_step = 1.5 * IQR
        
        # Determine a list of indices of outliers for feature col
        outlier_list_col = df[(df[col] < Q1 - outlier_step) | (df[col] > Q3 + outlier_step )].index
        
        # append the found outlier indices for col to the list of outlier indices 
        outlier_indices.extend(outlier_list_col)
        
    # select observations containing more than 2 outliers
    outlier_indices = Counter(outlier_indices)        
    multiple_outliers = list( k for k, v in outlier_indices.items() if v > n )
    
    return multiple_outliers   

# detect outliers from Age, SibSp , Parch and Fare
Outliers_to_drop = detect_outliers(train,2,["Age","SibSp","Parch","Fare"])

train.loc[Outliers_to_drop] # show the outliers rows

#Drop outliers

train = train.drop(Outliers_to_drop, axis = 0).reset_index(drop=True)

joining train and test set

#joining train and test set
train_len = len(train)
dataset = pd.concat(objs=[train, test], axis=0).reset_index(drop=True)

check for null and missing values

#check for null and missing values

#Fill empty and NaNs values with NaN
dataset = dataset.fillna(np.nan)

#check for null values

dataset.isnull().sum()

#Infos

train.info()
train.isnull().sum()

train.head()

train.dtypes

## Summarize data

train.describe()

Feature analysis

Numerical values

#Correlation matrix between numerical values (SibSp Parch Age and Fare values) and Survived

g = sns.heatmap(train[['Survived','SibSp','Parch','Age','Fare']].corr(),annot=True, fmt= ".2f", cmap = "coolwarm")

#SibSP

g= sns.factorplot(x="SibSp", y="Survived", data=train, kind="bar",size=6 , palette = "muted")
g.despine(left=True)
g = g.set_ylabels("survival probability")

#Parch

g = sns.factorplot(x="Parch", y ="Survived", data=train,kind="bar",size=6,palette="muted")
g.despine(left=True)
g = g.set_ylabels("survival probability")

#Age
g = sns.FacetGrid(train, col="Survived")
g = g.map(sns.distplot, "Age")

# Explore Age distibution 
g = sns.kdeplot(train["Age"][(train["Survived"] == 0) & (train["Age"].notnull())], color="Red", shade = True)
g = sns.kdeplot(train["Age"][(train["Survived"] == 1) & (train["Age"].notnull())], ax =g, color="Blue", shade= True)
g.set_xlabel("Age")
g.set_ylabel("Frequency")
g = g.legend(["Not Survived","Survived"])

#Fare

dataset["Fare"].isnull().sum() # 1

dataset["Fare"] = dataset["Fare"].fillna(dataset["Fare"].median())

g = sns.distplot(dataset["Fare"], color="m",label="Skewness : %.2f"%(dataset["Fare"].skew()))
g = g.legend(loc="best")

dataset["Fare"] = dataset["Fare"].map(lambda i: np.log(i) if i > 0 else 0)

g = sns.distplot(dataset["Fare"], color="b", label = "Skewness : %.2f"%(dataset['Fare'].skew()))
g = g.legend(loc="best")

Categorical values

#sex

g = sns.barplot(x="Sex",y="Survived",data=train)
g = g.set_ylabel("Survival Probability")

train[["Sex","Survived"]].groupby("Sex").mean()

#Pclass
g = sns.factorplot(x="Pclass", y="Survived", data= train, kind="bar",size =6,palette="muted")
g.despine(left=True)
g =  g.set_ylabels("Survival probability")

# Explore Pclass vs Survived by Sex
g = sns.factorplot(x="Pclass", y="Survived", hue="Sex", data=train,
                   size=6, kind="bar", palette="muted")
g.despine(left=True)
g = g.set_ylabels("survival probability")

#Embarked

dataset['Embarked'].isnull().sum() #2

dataset["Embarked"] = dataset["Embarked"].fillna("S")

g = sns.factorplot(x="Embarked", y="Survived", data=train, size=6, kind="bar", palette="muted")
g.despine(left=True)
g = g.set_ylabels("survival probability")

g = sns.factorplot("Pclass", col="Embarked", data=train, size=6, kind="count", palette="muted")
g.despine(left=True)
g =  g.set_ylabels("Count")