Project 5 - K-Means Clustering - Duplicate

# import libraries and K-Means function # import libraries and K-Means function import numpy as np import pandas as pd from pandas import DataFrame, Series from sklearn.cluster import KMeans import matplotlib.pyplot as plt import seaborn as sns

# Create dataframe for data df = pd.read_csv('cereal.csv') df.head()

# drop features we aren't using or create a new dataframe with only the features we want df_mod = df.drop(columns =['name','type','calories','protein','fat','sodium','fiber','potass','vit df_mod.head()

# Check to see if any instances have NaN for entries using .info

# Check to see if any cereals have negative values for sugars or carbohydrates; if 2 or less cereals, drop those # data instances; otherwise replace negative values with 0

# set background grid for plots sns.set_style( 'whitegrid')

# Plot number of products per manufacturer

# There is only one cereal from American Home Foods Company so we drop that data sample # # Type df[df.mfr == 'A'] and it will give you all data from this manufacturer. # Make sure you set df = drop command; use command to make sure it was deleted #

# For plots we would like the name of manufacturer instead of just "N" or "Q" # Use .map or .apply # # Then drop 'mfr' column #

# Plot to see which manufacturer has highest rated cereals

# Which cereal is rated highest?

# Look at sugars per brand by plotting

# Get data for clustering

# Add column to dataframe for this clusters, say sugars_clusters

# Plot clusters

# Determine which cluster number corresponds to lowest, middle and highest level and create a new # column in dataframe using .map # #

# How are cereals distributed among the 3 levels?

# Which cereals have the highest sugar levels #

# Which cereals have the lowest sugar levels #

# If you eat a particular cereal like Apple Jacks, Froot Loops, etc. what cluster is it in? my_cereal = 'Apple Jacks' print (f"The data instance and sugar cluster for {my_cereal} is ", \ df[df.name == my_cereal].sugars_clusters )