# -*- coding: utf-8 -*-
"""ASS 03.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1RX0dQAWd5l79JPyqHedCp_mi6Il4aU93
"""
# Commented out IPython magic to ensure Python compatibility.
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt #simple data visualization
# %matplotlib inline
import seaborn as sns #some advanced data visualizations
import warnings
warnings.filterwarnings(’ignore’) # to get rid of warnings
plt.style.use(’seaborn-white’) #defining desired style of viz
import os
for dirname, _, filenames in os.walk(’/kaggle/input’):
for filename in filenames:
print(os.path.join(dirname, filename))
"""# New Section"""
from google.colab import drive
drive.mount(’/content/drive’)
df = pd.read_csv(’/content/penguins_size.csv’)
original = df.copy()
print(’Dataset has’, df.shape[0] , ’rows and’, df.shape[1], ’columns’)
df.info()
df.describe()
df.isnull().sum()
df.head(10)
plt.rcParams[’figure.figsize’] = (10,7)
df[’species’].value_counts(normalize = True).plot(kind = ’bar’, color = ’seagreen’, linewidth = 1, edgecolor
= ’k’)
plt.title(’Penguin Species’)
plt.xlabel(’Species’)
plt.ylabel(’% (100s)’)
plt.xticks(rotation = 360)
plt.show()
df[’island’].value_counts(normalize = True).plot(kind = ’bar’, color = ’seagreen’, linewidth = 1, edgecolor = ’
k’)
plt.title(’Islands where Penguins live’)
plt.xlabel(’Island’)
plt.ylabel(’% (100s)’)
plt.xticks(rotation = 360)
plt.show()
df[’sex’].value_counts(normalize = True).plot(kind = ’bar’, color = ’seagreen’, linewidth = 1, edgecolor = ’k’)
plt.title(’Penguins - Sex’)
plt.xlabel(’Sex’)
plt.ylabel(’% (100s)’)
plt.xticks(rotation = 360)
plt.show()
def ecdf(x):
n = len(x)
a = np.sort(x)
b = np.arange(1, 1 + n) / n
plt.subplot(211)
plt.plot(a, b, marker = ’.’, linestyle = ’None’, c = ’seagreen’)
mean_x = np.mean(x)
plt.axvline(mean_x, c = ’k’, label = ’Mean’)
plt.title(’ECDF’)
plt.legend()
plt.show()
plt.subplot(212)
sns.distplot(x, color = ’r’)
plt.title(’Probability Density Function’)
plt.show()
ecdf(df[’culmen_length_mm’])
ecdf(df[’culmen_depth_mm’])
ecdf(df[’flipper_length_mm’])
ecdf(df[’body_mass_g’])
def box(f):
sns.boxplot(y = f, x = ’species’, hue = ’sex’,data = df)
plt.title(f)
plt.show()
box(’culmen_length_mm’)
box(’culmen_depth_mm’)
box(’flipper_length_mm’)
box(’body_mass_g’)
sns.pairplot(df, hue = ’species’)
plt.show()
new_df = original.copy()
new_df[’culmen_length_mm’].fillna(np.mean(original[’culmen_length_mm’]), inplace = True)
new_df[’culmen_depth_mm’].fillna(np.mean(original[’culmen_depth_mm’]), inplace = True)
new_df[’flipper_length_mm’].fillna(np.mean(original[’flipper_length_mm’]), inplace = True)
new_df[’body_mass_g’].fillna(np.mean(original[’body_mass_g’]), inplace = True)
new_df[’sex’].fillna(original[’sex’].mode()[0], inplace = True)
new_df.head()
new_df.isnull().sum()
