data_loading.py

# -*- coding: utf-8 -*-
"""Data Loading.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1A2Uw-sUxi6iu-OmeodPQaW5vRTfpMQwS

#**1 DATA LOADING**

##**1.1 LOADING LIBRARIES**
"""

# Import necessary libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import missingno as msno

# Standard scaler
from sklearn.preprocessing import StandardScaler

# Libraries for hierarchical clustering
from scipy.cluster.hierarchy import linkage, fcluster, dendrogram
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA

"""##**1.2 LOADING DATASET**"""

# Load data from url
url= '/content/russian_alcohol_consumption.csv'
df = pd.read_csv(url)
df.head()

"""We have access to the per capita sales of wine, beer, vodka, champagne and brandy in Russia between 1998 and 2016."""

# Number of rows and columns
df.shape

# Basic info about our dataset
df.info()

"""The data has 1615 entries and 7 different features. Based on the provider's instructions, these features include:

1.   **"year" -** year (1998-2016)
2.   **"region" -** name of a federal subject of Russia. It could be oblast, republic, krai, autonomous okrug, federal city and a single autonomous oblast
3.   **"wine" -** sale of wine in litres by year per capita
4.   **"beer" -** sale of beer in litres by year per capita
5.   **"vodka" -** sale of vodka in litres by year per capita
6.   **"champagne" -** sale of champagne in litres by year per capita
7.   **"brandy" -** sale of brandy in litres by year per capita

"""