def test_titanic():
train_df = titanic()[0].fillna(-999)
X, y = train_df.drop('Survived', axis=1), train_df.Survived
categorical_features_indices = np.where(X.dtypes != np.float)[0]
model = CatBoostClassifier(iterations=5)
model.fit(X, y, cat_features=categorical_features_indices)
preds = model.predict(X)
def build_titanic_dataset():
df_train, df_test = titanic()
df_train.fillna(-999, inplace=True)
df_test.fillna(-999, inplace=True)
X = df_train.drop('Survived', axis=1) # X: train feature
y = df_train.Survived # y: train label
# if the feature value type != float, then be treat as a categorial feature
cate_feat_idx = np.where(X.dtypes != np.float)[0]
x_train, x_vali, y_train, y_vali = train_test_split(X,
y,
train_size=0.75,
random_state=42)
x_test = df_test
return X, y, x_train, x_vali, y_train, y_vali, x_test, cate_feat_idx
def main(**args):
titanic_train, _ = titanic()
titanic_train.fillna(-999, inplace=True)
cols = [
'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch', 'Ticket', 'Fare',
'Cabin', 'Embarked'
]
train_sz = int(titanic_train.shape[0] * 0.1)
x_train = titanic_train[:train_sz][cols]
y_train = titanic_train[:train_sz]['Survived'].astype(int)
x_test = titanic_train[train_sz:][cols]
y_test = titanic_train[train_sz:]['Survived'].astype(int)
try:
model = CatBoostClassifier(random_seed=42, **args)
model.fit(x_train, y_train, [1, 2, 6, 8, 9], silent=True)
accuracy = model.score(x_test, y_test)
print(-accuracy)
except:
print(0)
def load_test(self):
_, self.df_test = titanic()
self.df_test["Survived"] = -1
def load_train(self):
self.df_train, _ = titanic()
from pagi.models.binary_classifiers import get_CatBoostClassifier
if __name__ == "__main__":
from catboost.datasets import titanic
import numpy as np
train_df, test_df = titanic()
train_df.head()
train_df.fillna(-999, inplace=True)
test_df.fillna(-999, inplace=True)
X = train_df.drop('Survived', axis=1)
y = train_df.Survived
print(X.dtypes)
categorical_features_indices = np.where(X.dtypes != np.float)[0]
from sklearn.model_selection import train_test_split
X_train, X_validation, y_train, y_validation = train_test_split(
X, y, train_size=0.75, random_state=42)
X_test = test_df
model = get_CatBoostClassifier()
model.fit(X_train,
y_train,
cat_features=categorical_features_indices,
eval_set=(X_validation, y_validation),
plot=True)
Objective: Catboost algorithm implementation
Author: Samuel Adebayo
Blog: https://dataaspirant.com
Date: 2021-01-02
===============================================
"""
## import the libraries needed
import pandas as pd
import numpy as np
# Here we import our dataset from the CatBoost dataset library
from catboost.datasets import titanic
## The titanic dataset is made up of the train and test set, so we have to separate the data
titanic_train, titanic_test = titanic()
## Here we create a list to sort the columns so that the "Survived" column comes last
## This is because "Survived" is the target
column_sort = [
'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch', 'Ticket', 'Fare',
'Cabin', 'Embarked', 'Survived'
]
## Now we apply the sorted columns to the train data
train = titanic_train[column_sort]
train.set_index('Pclass') ## Not necessary just to get of the default index
test = titanic_test
train.head()
def _data_loading(self):
# The data for this tutorial can be obtained from [this page](https://www.kaggle.com/c/titanic/data)
self.train_df, self.test_df = titanic()
print(self.train_df.head())
# coding=utf-8
import json
import os
import numpy as np
from catboost import CatBoostClassifier, Pool, cv
from sklearn.model_selection import train_test_split
from catboost.datasets import titanic
# get training data
train, test = titanic()
# remove nans
train, test = train.fillna(-999), test.fillna(-999)
# split into train and test
X, y = train.drop(['PassengerId', 'Survived'], axis=1), train['Survived']
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8)
# define categorical features
cat_indices = np.where(X_train.dtypes != float)[0]
# define model params
params = {
'iterations': 1000,
'depth': 2,
'loss_function': 'Logloss',
'eval_metric': 'F1',
'use_best_model': True,