In [6]:

    

import xgboost as xgb
from sklearn.ensemble import GradientBoostingClassifier as GBC


    

In [8]:

    

import pandas as pd
import numpy as np
import xgboost as xgb
from sklearn import preprocessing
from sklearn.cross_validation import train_test_split

seed = 260681

train = pd.read_csv('kaggle/train.csv')
test = pd.read_csv('kaggle/test.csv')

y = train.QuoteConversion_Flag.values
train = train.drop(['QuoteNumber', 'QuoteConversion_Flag'], axis=1)
test = test.drop('QuoteNumber', axis=1)

# Lets play with some dates
train['Date'] = pd.to_datetime(pd.Series(train['Original_Quote_Date']))
train = train.drop('Original_Quote_Date', axis=1)

test['Date'] = pd.to_datetime(pd.Series(test['Original_Quote_Date']))
test = test.drop('Original_Quote_Date', axis=1)

train['Year'] = train['Date'].apply(lambda x: int(str(x)[:4]))
train['Month'] = train['Date'].apply(lambda x: int(str(x)[5:7]))
train['weekday'] = train['Date'].dt.dayofweek


test['Year'] = test['Date'].apply(lambda x: int(str(x)[:4]))
test['Month'] = test['Date'].apply(lambda x: int(str(x)[5:7]))
test['weekday'] = test['Date'].dt.dayofweek

train = train.drop('Date', axis=1)
test = test.drop('Date', axis=1)

train = train.fillna(-1)
test = test.fillna(-1)

for f in train.columns:
    if train[f].dtype=='object':
        print(f)
        lbl = preprocessing.LabelEncoder()
        lbl.fit(list(train[f].values) + list(test[f].values))
        train[f] = lbl.transform(list(train[f].values))
        test[f] = lbl.transform(list(test[f].values))

clf = xgb.XGBClassifier(n_estimators=25,
                        nthread=-1,
                        max_depth=10,
                        learning_rate=0.025,
                        silent=True,
                        subsample=0.8,
                        colsample_bytree=0.8)
                        
xgb_model = clf.fit(train, y, eval_metric="auc")


    

    




Field6
Field10
Field12
CoverageField8
CoverageField9
SalesField7
PersonalField7
PersonalField16
PersonalField17
PersonalField18
PersonalField19
PropertyField3
PropertyField4
PropertyField5
PropertyField7
PropertyField14
PropertyField28
PropertyField30
PropertyField31
PropertyField32
PropertyField33
PropertyField34
PropertyField36
PropertyField37
PropertyField38
GeographicField63
GeographicField64

In [11]:

    

from sklearn.preprocessing import LabelEncoder
LabelEncoder?


    

In [10]:

    

xgb_model.score(train, y)


    

    
Out[10]:





0.92431534824143924