In [11]:

    

import numpy as np
import pandas as pd
from sklearn import preprocessing


    

In [15]:

    

df = pd.read_csv("train.csv")
df.loc[df["Sex"] == 'female',"Sex"] = 0
df.loc[df["Sex"] == 'male',"Sex"] = 1

print(len(df))
df = df.fillna(value="Not available")
df_test = pd.read_csv("test.csv")
df_train = df[0:600]
df_cross_validate = df[601:]


    

    




male
female
female
female
male
male
male
male
female
female
female
female
male
male
female
female
male
male
female
female
male
male
female
male
female
female
male
male
female
male
male
female
female
male
male
male
male
male
female
female
female
female
male
female
female
male
male
female
male
female
male
male
female
female
male
male
female
male
female
male
male
female
male
male
male
male
female
male
female
male
male
female
male
male
male
male
male
male
male
female
male
male
female
male
female
female
male
male
female
male
male
male
male
male
male
male
male
male
female
male
female
male
male
male
male
male
female
male
male
female
male
female
male
female
female
male
male
male
male
female
male
male
male
female
male
male
male
male
female
male
male
male
female
female
male
male
female
male
male
male
female
female
female
male
male
male
male
female
male
male
male
female
male
male
male
male
female
male
male
male
male
female
male
male
male
male
female
female
male
male
male
male
female
male
male
male
male
female
male
male
female
male
male
male
female
male
female
male
male
male
female
male
female
male
female
female
male
male
female
female
male
male
male
male
male
female
male
male
female
male
male
female
male
male
male
female
female
male
female
male
male
male
male
male
male
male
male
male
male
female
female
male
male
female
male
female
male
female
male
male
female
female
male
male
male
male
female
female
male
male
male
female
male
male
female
female
female
female
female
female
male
male
male
male
female
male
male
male
female
female
male
male
female
male
female
female
female
male
male
female
male
male
male
male
male
male
male
male
male
female
female
female
male
female
male
male
male
female
male
female
female
male
male
female
male
male
female
female
male
female
female
female
female
male
male
female
female
male
female
female
male
male
female
female
male
female
male
female
female
female
female
male
male
male
female
male
male
female
male
male
male
female
male
male
male
female
female
female
male
male
male
male
male
male
male
male
female
female
female
female
male
male
female
male
male
male
female
female
female
female
male
male
male
male
female
female
female
male
male
male
female
female
male
female
male
male
male
female
male
female
male
male
male
female
female
male
female
male
male
female
male
male
female
male
female
male
male
male
male
female
male
male
female
male
male
female
female
female
male
female
male
male
male
female
male
male
female
female
male
male
male
female
female
male
male
female
female
female
male
male
female
male
male
female
male
male
female
male
female
male
male
male
male
male
male
male
male
female
female
male
male
male
male
male
male
male
male
male
male
female
male
male
female
female
female
male
male
male
male
female
male
male
male
female
male
female
female
male
male
male
male
male
male
male
male
male
female
male
female
male
male
female
female
female
female
male
female
male
male
male
male
male
male
female
male
male
female
male
female
male
female
male
male
female
male
male
female
male
male
male
female
male
male
female
female
female
male
female
male
female
female
female
female
male
male
male
female
male
male
male
male
male
male
male
female
male
female
male
female
female
male
male
male
male
female
male
male
female
male
male
male
female
male
female
male
male
female
female
female
male
female
female
male
male
male
female
male
male
male
male
male
female
male
female
male
male
female
male
male
male
female
male
male
male
male
male
male
male
female
female
female
male
female
male
male
female
male
female
female
male
male
male
male
male
male
male
male
female
male
male
male
male
male
male
female
female
male
male
female
male
male
female
female
male
female
male
male
male
male
female
male
female
male
female
female
male
male
female
male
male
male
male
male
male
male
male
male
male
male
female
female
male
male
male
male
male
male
female
female
male
female
male
male
male
male
male
male
male
male
female
male
female
male
male
male
male
male
female
male
male
female
male
female
male
male
male
female
male
female
male
female
male
male
male
male
male
female
female
male
male
female
male
male
male
male
male
female
female
male
female
female
male
male
male
male
male
female
male
male
male
male
male
female
male
male
male
male
female
male
male
female
male
male
male
female
male
male
male
male
female
male
male
male
female
male
female
male
female
male
male
male
male
female
male
female
male
male
female
male
female
female
female
male
male
male
male
female
male
male
male
male
male
female
male
male
male
female
female
male
female
male
female
male
male
male
male
male
female
male
female
male
male
male
female
male
male
female
male
male
male
female
male
male
female
male
male
male
male
male
female
female
male
male
male
male
female
male
male
male
male
male
male
female
male
male
male
male
male
male
female
male
male
female
female
female
female
female
male
female
male
male
male
female
female
male
female
female
male
male
male
male
female
male
male
female
female
male
male
male
female
female
male
female
male
male
female
male
female
female
male
male
891

In [ ]:

    

Features = ["PassengerId","Survived","Pclass","Sex","Age","Fare","Embarked"]
Passanger_data = df["PassengerId"]
Survived_data = df["Survived"]
Pclass_data = df["Pclass"]
Sex_data = df["Sex"]
Age_data = df["Age"]
Fare_data = df["Fare"]
Embarked_data = df["Embarked"]


    

In [12]:

    

feautre_list = ["PassengerId","Survived","Sex","Age","Fare"]
df_train_scaled = preprocessing.scale(df_train)


    

    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-12-68062365ff3d> in <module>()
      1 feautre_list = ["PassengerId","Survived","Sex","Age","Fare"]
----> 2 df_train_scaled = preprocessing.scale(df_train)

/usr/lib64/python3.5/site-packages/sklearn/preprocessing/data.py in scale(X, axis, with_mean, with_std, copy)
    127     X = check_array(X, accept_sparse='csc', copy=copy, ensure_2d=False,
    128                     warn_on_dtype=True, estimator='the scale function',
--> 129                     dtype=FLOAT_DTYPES)
    130     if sparse.issparse(X):
    131         if with_mean:

/usr/lib64/python3.5/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    380                                       force_all_finite)
    381     else:
--> 382         array = np.array(array, dtype=dtype, order=order, copy=copy)
    383 
    384         if ensure_2d:

ValueError: could not convert string to float: 'C'