In [1]:
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline
In [2]:
#importing the data
train_df = pd.read_csv('train.csv', header=0)
train_df.head()
Out[2]:
ID y X0 X1 X2 X3 X4 X5 X6 X8 ... X375 X376 X377 X378 X379 X380 X382 X383 X384 X385
0 0 130.81 k v at a d u j o ... 0 0 1 0 0 0 0 0 0 0
1 6 88.53 k t av e d y l o ... 1 0 0 0 0 0 0 0 0 0
2 7 76.26 az w n c d x j x ... 0 0 0 0 0 0 1 0 0 0
3 9 80.62 az t n f d x l e ... 0 0 0 0 0 0 0 0 0 0
4 13 78.02 az v n f d h d n ... 0 0 0 0 0 0 0 0 0 0

5 rows × 378 columns

In [3]:
train_df.get_dtype_counts()
Out[3]:
float64      1
int64      369
object       8
dtype: int64
In [ ]: