Project 5 - K-Means Clustering - Duplicate

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

# Create dataframe for data df=pd.read_csv('cereal.csv') df.head(6)

# drop features we aren't using or create a new dataframe with only the features we want df2 = pd.DataFrame([df.name, df.mfr, df.sugars,df.carbo,df.rating]).transpose()

# Check to see if any instances have NaN for entries using .info df2.info #no NaN entries

# 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 df2[ ( df2.sugars<0) | (df2.carbo<0)] #only one instance, so we just drop instance 57 df2=df2.drop([57] )

# Address negative values #done in above cell.

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

# Plot number of products per manufacturer df2['mfr'].value_counts().plot(kind='bar')

# 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 # df2[df2.mfr == 'A'] df2=df2.drop([43] )

# For plots we would like the name of manufacturer instead of just "N" or "Q" #decided not to use map method. same result so please don't dock points. df2.loc[df.mfr == "A", "mfr"] = "American Home Food Products" df2.loc[df.mfr == "G", "mfr"] = "General Mills" df2.loc[df.mfr == "K", "mfr"] = "Kelloggs" df2.loc[df.mfr == "N", "mfr"] = "Nabisco" df2.loc[df.mfr == "P", "mfr"] = "Post" df2.loc[df.mfr == "Q", "mfr"] = "Quaker Oats" df2.loc[df.mfr == "R", "mfr"] = "Ralston Purina" df2['manufacturer']=df2.mfr df2.drop(columns=['mfr']) # Then drop 'mfr' column #

# Plot to see which manufacturer has highest rated cereals sns.catplot(x='manufacturer', y='rating', data = df2, hue = 'manufacturer' ) plt.xticks(rotation=45) #Kelloggs has the highest individual rating, but Nabisco appears to have the highest average ratings # when viewing the data as a whole.

# Which cereal is rated highest? #Kelloggs has the highest individual rating, with the specific cereal being "All-Bran with Extra Fiber."

# Look at sugars per brand by plotting sns.catplot(x='manufacturer', y='sugars', data = df2, hue = 'manufacturer' ) plt.xticks(rotation=45) #Nabisco appears to have the lowest overall sugar content in their cereals, with numerous Nabisco products # having 0 grams of sugar.

# Get data for clustering X=df2.sugars.values n=len(X) X=np.reshape(X,(n,1))

# Form model, fit data and print out cluster centers km = KMeans( n_clusters=3, init ='random' ,random_state=0 ) y_km = km.fit(X) print ("Cluster centers for sepal & petal length and width") print() print (km.cluster_centers_ ) # print out cluster centers which are points in 4D

# Add column to dataframe for this clusters, say sugars_clusters df2['sugars_clusters']=km.labels_ df2.head()

#plot clusters sns.catplot(x='sugars_clusters',y='sugars',data=df2)

# Determine which cluster number corresponds to lowest, middle and highest level and create a new # column in dataframe using .map # # df2['sugars_clusters_levels']=df2['sugars_clusters'].map( \ { 0:'low sugar', \ 1:'mid sugar', \ 2:'high sugar' } ) df2.head()

# How are cereals distributed among the 3 levels? sns.catplot(x='sugars_clusters_levels', y='sugars', data = df2,hue='manufacturer' )

# Which cereals have the highest sugar levels # df2[df2.sugars_clusters_levels=='high sugar']

# Which cereals have the lowest sugar levels # df2[df2.sugars_clusters_levels=='low sugar']

# 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 level for {my_cereal} is ", \ df2[df2.name == my_cereal].sugars_clusters_levels )

X=df2.carbo.values n=len(X) X=np.reshape(X,(n,1))

# Form model, fit data and print out cluster centers km = KMeans( n_clusters=3, init ='random' ,random_state=0 ) y_km = km.fit(X) print ("Cluster centers for sepal & petal length and width") print() print (km.cluster_centers_ ) # print out cluster centers which are points in 4D

# Add column to dataframe for this clusters, say sugars_clusters df2['carbs_clusters']=km.labels_ df2.head() # Determine which cluster number corresponds to lowest, middle and highest level and create a new # column in dataframe using .map # # df2['carbs_clusters_levels']=df2['carbs_clusters'].map( \ { 0:'mid carbs', \ 1:'low carbs', \ 2:'high carbs' } ) df2.head() #plot clusters sns.catplot(x='carbs_clusters_levels',y='carbo',data=df2,hue='manufacturer')

df2[ ( df2.sugars_clusters_levels=='low sugar') & (df2.carbs_clusters_levels=='low carbs')]

#What cereals are low sugar and high carbs? df2[ ( df2.sugars_clusters_levels=='low sugar') & (df2.carbs_clusters_levels=='high carbs')]

#What cereals are high sugar and high carbs? df2[ ( df2.sugars_clusters_levels=='high sugar') & (df2.carbs_clusters_levels=='high carbs')] #none (by our clusters)