डेटा साइंस में आपका पहला कदम। टाइटैनिक

एक छोटा सा परिचय

पहला कदम

दूसरा कदम

import pandas as pd
import numpy as np

dataset = pd.read_csv('train.csv')

dataset.head()

X = dataset.iloc[ : , 2 : ]
y = dataset.iloc[ : , 1 : 2 ]

X.head()

y.head()

count = ['Name', 'Ticket', 'Cabin', 'Embarked']
X.drop(count, inplace=True, axis=1)

तीसरा कदम

X = np.array(X)
y = np.array(y)

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder

ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [1])],
                       remainder='passthrough')
X = np.array(ct.fit_transform(X))

from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
imputer.fit(X)
X = imputer.transform(X)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X[:, 2:] = sc.fit_transform(X[:, 2:])

चौथा चरण

from sklearn.ensemble import GradientBoostingClassifier
gbc = GradientBoostingClassifier(learning_rate=0.5, max_depth=5, n_estimators=150)
gbc.fit(X, y)

चरण पाँच निष्कर्ष

X_test = pd.read_csv('test.csv', index_col=0)

count = ['Name', 'Ticket', 'Cabin', 'Embarked']
X_test.drop(count, inplace=True, axis=1)

X_test = np.array(X_test)

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [1])],
                       remainder='passthrough')
X_test = np.array(ct.fit_transform(X_test))

from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
imputer.fit(X_test)
X_test = imputer.transform(X_test)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_test[:, 2:] = sc.fit_transform(X_test[:, 2:])

gbc_predict = gbc.predict(X_test)

np.savetxt('my_gbc_predict.csv', gbc_predict, delimiter=",", header = 'Survived')