xordux

import pandas as pd
# using Kaggle's famous Titanic Dataset below
data = pd.read_csv("train.csv")

profile = data.profile_report(title='Titanic Dataset Profile')
profile.to_file(output_file="output.html")

xordux

import pandas as pd

# using Kaggle's famous Titanic Dataset below
data = pd.read_csv("train.csv")
print(data.describe(include = 'all'))

xordux

import pandas as pd
from sklearn.base import TransformerMixin
from xgboost import XGBClassifier
from sklearn.pipeline import Pipeline
from sklearn import metrics


class DataTransformer(TransformerMixin):  
    def cabin(self, val):
        if type(val) != str or val == "":

xordux

import pandas as pd
from sklearn.base import TransformerMixin
from xgboost import XGBClassifier
from sklearn.pipeline import Pipeline
from sklearn import metrics


class DataTransformer(TransformerMixin):  
    def fit(self, X, y=None):
        assert isinstance(X, pd.DataFrame)

xordux

from sklearn.base import TransformerMixin
class DataTransformer(TransformerMixin):
    def fit(self, X, y=None):
        return self
    def transform(self, X, y=None):
        return X

xordux

from sklearn.base import TransformerMixin
class DataTransformer(TransformerMixin):
    def fit(self, X, y=None):
        return self
    def transform(self, X, y=None):
        return X