I have been working on a project which i took from
kaggle. I didn't get the result as mentioned in the website. What am I doing wrong here?
import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns train = pd.read_csv('../data/dont-overfit/train.csv') test = pd.read_csv('../data/dont-overfit/test.csv') train[train.columns[2:]].std().plot('hist') train[train.columns[2:]].mean().plot('hist') plt.title('Distribution of means/stds of all columns') plt.show() print(train.isnull().any().any()) print('Distribution of first 28 columns') plt.figure(figsize=(26,24)) for i, col in enumerate(list(train)[2:30]): plt.subplot(7, 4, i+1) plt.hist(train[col]) plt.title(col) plt.show()
Here is the post