
from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


from typing import Sequence, Tuple
from itertools import combinations, chain
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import sklearn
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans, AgglomerativeClustering, SpectralClustering
from scipy.cluster.hierarchy import dendrogram
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import silhouette_samples, silhouette_score
from sklearn.tree import DecisionTreeClassifier, plot_tree


df_Fel = pd.read_csv('/content/drive/MyDrive/Amazon hackathon/Columbia_Hackathon_Data_Dogfood.csv')


sns.pairplot(df_Fel.drop(columns=['sale_id', 'customer_id', 'product_id']), hue = 'prime', palette=['b', 'r'], plot_kws=dict(alpha=0.4))
plt.show()


df_Fel.drop(columns =['sale_id','customer_id', 'product_id'], inplace=True) #drop sale_id, customer_id, product_id


scaler = StandardScaler()
df_Fel_scale = df_Fel.copy()
df_Fel_scale[['price']] = scaler.fit_transform(df_Fel_scale[['price']])
df_Fel_scale.head()


df_Fel_onehot = pd.get_dummies(df_Fel_scale, drop_first=False)#, columns = (['sale_date','ad_exp','income','gender','marital', 'education','age']))
df_Fel_onehot.head()


def calculate_k_mean(n_cluster: int, X: Sequence)-> Tuple[float, Sequence, Sequence, sklearn.cluster._kmeans.KMeans]:
    '''
    General Function to returns commonly used metrics for K-Means Clustering and the fitted instance
    '''
    kmean = KMeans(n_clusters = n_cluster, random_state=24)
    cluster_labels = kmean.fit_predict(X)
    return kmean.inertia_, cluster_labels, kmean.cluster_centers_, kmean


log = [] 
silhoettes = True
k_range = range(2,15) # Range of k values

for k in k_range:
    inertia, cluster_labels, _, _ = calculate_k_mean(k, df_Fel_onehot) # Fitting the model
    if silhoettes: # Generate Silhoettes Score
        silhoettes_avg = silhouette_score(df_Fel_onehot, cluster_labels)
        log.append([k, inertia, silhoettes_avg])
        continue
    log.append([k, inertia])


plot_df = pd.DataFrame(
    log, columns = [
        'k', 'Inertias (Sum of squared distances to Nearest Cluster Centroids)', 'Silhouette Coefficient'
        ]
    )
fig, axes = plt.subplots(1,2, figsize=(18,7))
sns.lineplot(
    x='k', y='Inertias (Sum of squared distances to Nearest Cluster Centroids)', 
    data = plot_df, marker= 'o', ax = axes[0])
axes[0].set_title("Elbow Method (Inertia)")
sns.lineplot(x='k', y='Silhouette Coefficient', data=plot_df, marker='o', ax = axes[1])
axes[1].set_title("Silhoettes Score")
plt.show()


def silhouette_analysis_with_pca(n_clusters : int,  X: Sequence):
    '''
    Perform Silhoette Analysis and Visualising the clusters generated using PCA

    Reference: https://scikit-learn.org/stable/auto_examples/cluster/plot_kmeans_silhouette_analysis.html
    '''
    
    # Perform K-Mean Clustering
    _, cluster_labels, cluster_centroids, kmean = calculate_k_mean(n_clusters, X)

    # Compute Individual Silhoette Score
    silhoettes_avg = silhouette_score(X, cluster_labels)

    # Compute Average Silhoette Score
    sample_silhouette_values = silhouette_samples(X, cluster_labels)

    # Create a subplot with 1 row and 2 columns
    fig, (ax1, ax2) = plt.subplots(1, 2)
    fig.set_size_inches(18, 7)

    ################################### Silhouette Plot #############################################
 
    # The (n_clusters+1)*10 is for inserting blank space between silhouette
    # plots of individual clusters, to demarcate them clearly.
    ax1.set_xlim([-0.1, 1])
    ax1.set_ylim([0, len(df_Fel_onehot) + (n_clusters + 1) * 10])
    y_lower = 10

    # Assign colours for different cluster
    for i in range(n_clusters):
         # Aggregate the silhouette scores for samples belonging to
         # cluster i, and sort them
         ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]
         ith_cluster_silhouette_values.sort()
         size_cluster_i = ith_cluster_silhouette_values.shape[0]
         y_upper = y_lower + size_cluster_i
         color = cm.nipy_spectral(float(i) / n_clusters)
         ax1.fill_betweenx(np.arange(y_lower, y_upper),
                           0, ith_cluster_silhouette_values,
                           facecolor=color, edgecolor=color, alpha=0.7)
         # Label the silhouette plots with their cluster numbers at the middle
         ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
         # Compute the new y_lower for next plot
         y_lower = y_upper + 10  # 10 for the 0 samples

    ax1.set_title("The Silhouette Plot for the various clusters.")
    ax1.set_xlabel("The silhouette coefficient values")
    ax1.set_ylabel("Cluster label")
    # The vertical line for average silhouette score of all the values
    ax1.axvline(x=silhoettes_avg, color="red", linestyle="--")
    ax1.set_yticks([])  # Clear the yaxis labels / ticks
    ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])

    ################################### PCA Plot #############################################
 
    # Compute PCA with only First 2 Number of Component
    pca2 = PCA(n_components=2)
    sample_pca2 = pca2.fit_transform(X)

    # Plotting the PCA graph
    colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters)
    ax2.scatter(sample_pca2[:,0], sample_pca2[:,1], marker='.', s=75, lw=0, alpha=1,
            c=colors, edgecolor='k')

    # Labeling the clusters
    centers = cluster_centroids.dot(pca2.components_.T) # Calculate New Cluster Positions after PCA

    # Labelling each cluster centroids
    #ax2.scatter(centers[:, 0], centers[:, 1], marker='o',
    #            c="white", alpha=1, s=200, edgecolor='k')
    #for i, c in enumerate(centers):
    #    ax2.scatter(c[0], c[1], marker='$%d$' % i, alpha=1,
    #               s=50, edgecolor='k')
   # ax2.set_title("The visualization of the PCA with total variance explained of {:.2f}%.".format(pca2.explained_variance_ratio_.sum()*100))
    #ax2.set_xlabel("Feature space for the 1st principle component")
    #ax2.set_ylabel("Feature space for the 2nd principle component")
    plt.suptitle(("Silhouette analysis for KMeans clustering on sample data "
                  "with n_clusters = %d" % n_clusters),
                 fontsize=14, fontweight='bold')

for i, k in enumerate(range(10,11)): # Analyse k = (4,5,6)
    silhouette_analysis_with_pca(n_clusters = k, X = df_Fel_onehot)
    plt.show()


inertia, cluster_labels, _, _ = calculate_k_mean(10, df_Fel_onehot)


inertia

59928172015.67202


labels = cluster_labels


len(labels)

8894


label0 = np.where(labels == 0)
label0
label0[0].shape

(1108,)


label1 = np.where(labels == 1)
label1
label1[0].shape

(642,)


label2 = np.where(labels == 2)
label2[0].shape

(1264,)


label3 = np.where(labels == 3)
label3[0].shape

(510,)


label4 = np.where(labels == 4)
label4[0].shape

(755,)


label5 = np.where(labels == 5)
label5[0].shape

(668,)


label6 = np.where(labels == 6)
label6[0].shape

(1066,)


label7 = np.where(labels == 7)
label7[0].shape

(877,)


label8 = np.where(labels == 8)
label8[0].shape

(1221,)


label9 = np.where(labels == 9)
label9[0].shape

(783,)


label0= label0[0] #convert from tuple to list
label1= label1[0]
label2= label2[0]
label3= label3[0]
label4= label4[0]
label5= label5[0]
label6= label6[0]
label7= label7[0]
label8= label8[0]
label9= label9[0]


df0= df_Fel_onehot[df_Fel_onehot.index.isin(label0)] #get rows from cluster based on index
df1= df_Fel_onehot[df_Fel_onehot.index.isin(label1)]
df2= df_Fel_onehot[df_Fel_onehot.index.isin(label2)]
df3= df_Fel_onehot[df_Fel_onehot.index.isin(label3)]
df4= df_Fel_onehot[df_Fel_onehot.index.isin(label4)]
df5= df_Fel_onehot[df_Fel_onehot.index.isin(label5)]
df6= df_Fel_onehot[df_Fel_onehot.index.isin(label6)]
df7= df_Fel_onehot[df_Fel_onehot.index.isin(label7)]
df8= df_Fel_onehot[df_Fel_onehot.index.isin(label8)]
df9= df_Fel_onehot[df_Fel_onehot.index.isin(label9)]


from statistics import mean
mean(df0['price']*df0['qty'])

-0.024019945030047857


mean(df1['price']*df1['qty'])

-0.018127835978210223


mean(df2['price']*df2['qty'])

0.10326014624762712


mean(df3['price']*df3['qty'])

0.09995315931784801


mean(df4['price']*df4['qty'])

-0.04742933551255805


mean(df5['price']*df5['qty'])

-0.021991431675108617


mean(df6['price']*df6['qty'])

0.06981661182760394


mean(df7['price']*df7['qty'])

-0.05458320917941718


mean(df8['price']*df8['qty'])

-0.03677272386123989


mean(df9['price']*df9['qty'])

-0.05638635074643973


columns_brand = ['product_brand_Alpha',
 'product_brand_Arf',
 'product_brand_Astro',
 'product_brand_Beam',
 'product_brand_Beethoven',
 'product_brand_Bezt',
 'product_brand_Bones',
 'product_brand_Choice',
 'product_brand_Flora',
 'product_brand_Garland',
 'product_brand_Hanover',
 'product_brand_Health One',
 'product_brand_Hearth',
 'product_brand_K99',
 'product_brand_Kastle',
 'product_brand_King',
 'product_brand_Omaha',
 'product_brand_Paws',
 'product_brand_Perro',
 'product_brand_Playtime',
 'product_brand_Rivera',
 'product_brand_Romero',
 'product_brand_Ruby',
 'product_brand_Seattle Gourmet',
 'product_brand_Top']
max_column = ''
max_count = -1
for column in columns_brand:
  count = df2[column].sum()
  print('max_column = {},  count = {}'.format(column, count))
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = product_brand_Alpha,  count = 416
max_column = product_brand_Arf,  count = 133
max_column = product_brand_Astro,  count = 10
max_column = product_brand_Beam,  count = 31
max_column = product_brand_Beethoven,  count = 14
max_column = product_brand_Bezt,  count = 209
max_column = product_brand_Bones,  count = 9
max_column = product_brand_Choice,  count = 53
max_column = product_brand_Flora,  count = 7
max_column = product_brand_Garland,  count = 45
max_column = product_brand_Hanover,  count = 12
max_column = product_brand_Health One,  count = 109
max_column = product_brand_Hearth,  count = 8
max_column = product_brand_K99,  count = 11
max_column = product_brand_Kastle,  count = 5
max_column = product_brand_King,  count = 30
max_column = product_brand_Omaha,  count = 10
max_column = product_brand_Paws,  count = 26
max_column = product_brand_Perro,  count = 12
max_column = product_brand_Playtime,  count = 6
max_column = product_brand_Rivera,  count = 14
max_column = product_brand_Romero,  count = 8
max_column = product_brand_Ruby,  count = 18
max_column = product_brand_Seattle Gourmet,  count = 43
max_column = product_brand_Top,  count = 25
max_column = product_brand_Alpha,  count = 416


from scipy.cluster.hierarchy import dendrogram, linkage

data = df_Fel_onehot
linkage_data = linkage(data, method = 'ward', metric='euclidean')
dendrogram(linkage_data)

plt.show()


hierarchical_cluster = AgglomerativeClustering(n_clusters = 10, affinity='euclidean', linkage='ward' )


labels = hierarchical_cluster.fit_predict(df_Fel_onehot)
print(labels)

[7 2 7 ... 4 0 0]


len(labels)

8894


label0 = np.where(labels == 0)
label0
label0[0].shape

(963,)


label1 = np.where(labels == 1)
label1
label1[0].shape

(685,)


label2 = np.where(labels == 2)
label2[0].shape

(1470,)


label3 = np.where(labels == 3)
label3[0].shape

(1108,)


label4 = np.where(labels == 4)
label4[0].shape

(1340,)


label5 = np.where(labels == 5)
label5[0].shape

(862,)


label6 = np.where(labels == 6)
label6[0].shape

(810,)


label7 = np.where(labels == 7)
label7[0].shape

(783,)


label8 = np.where(labels == 8)
label8[0].shape

(389,)


label9 = np.where(labels == 9)
label9[0].shape

(484,)


label0= label0[0] #convert from tuple to list
label1= label1[0]
label2= label2[0]
label3= label3[0]
label4= label4[0]
label5= label5[0]
label6= label6[0]
label7= label7[0]
label8= label8[0]
label9= label9[0]


df0= df_Fel_onehot[df_Fel_onehot.index.isin(label0)] #get rows from cluster based on index
df1= df_Fel_onehot[df_Fel_onehot.index.isin(label1)]
df2= df_Fel_onehot[df_Fel_onehot.index.isin(label2)]
df3= df_Fel_onehot[df_Fel_onehot.index.isin(label3)]
df4= df_Fel_onehot[df_Fel_onehot.index.isin(label4)]
df5= df_Fel_onehot[df_Fel_onehot.index.isin(label5)]
df6= df_Fel_onehot[df_Fel_onehot.index.isin(label6)]
df7= df_Fel_onehot[df_Fel_onehot.index.isin(label7)]
df8= df_Fel_onehot[df_Fel_onehot.index.isin(label8)]
df9= df_Fel_onehot[df_Fel_onehot.index.isin(label9)]

df1


from statistics import mean
mean(df0['price']*df0['qty'])

-0.015045486214909818


mean(df1['price']*df1['qty'])

-0.024412121773835907


mean(df2['price']*df2['qty'])

0.08744795926327455


mean(df3['price']*df3['qty'])

-0.024019945030047857


mean(df4['price']*df4['qty'])

-0.0200793420043912


mean(df5['price']*df5['qty'])

-0.052724937111071644


mean(df6['price']*df6['qty'])

0.06573791243837343


mean(df7['price']*df7['qty'])

-0.05638635074643973


mean(df8['price']*df8['qty'])

0.0837901853442486


mean(df9['price']*df9['qty'])

-0.020267132049387838

df8


column_list = df_Fel_onehot.columns.values.tolist()
column_list

['sns',
 'price',
 'qty',
 'zip',
 'lat',
 'lng',
 'prime',
 'sale_date_2021-10-01',
 'sale_date_2021-10-02',
 'sale_date_2021-10-03',
 'sale_date_2021-10-04',
 'sale_date_2021-10-05',
 'sale_date_2021-10-06',
 'sale_date_2021-10-07',
 'sale_date_2021-10-08',
 'sale_date_2021-10-09',
 'sale_date_2021-10-10',
 'sale_date_2021-10-11',
 'sale_date_2021-10-12',
 'sale_date_2021-10-13',
 'sale_date_2021-10-14',
 'sale_date_2021-10-15',
 'sale_date_2021-10-16',
 'sale_date_2021-10-17',
 'sale_date_2021-10-18',
 'sale_date_2021-10-19',
 'sale_date_2021-10-20',
 'sale_date_2021-10-21',
 'sale_date_2021-10-22',
 'sale_date_2021-10-23',
 'sale_date_2021-10-24',
 'sale_date_2021-10-25',
 'sale_date_2021-10-26',
 'sale_date_2021-10-27',
 'sale_date_2021-10-28',
 'sale_date_2021-10-29',
 'sale_date_2021-10-30',
 'sale_date_2021-10-31',
 'sale_date_2021-11-01',
 'sale_date_2021-11-02',
 'sale_date_2021-11-03',
 'sale_date_2021-11-04',
 'sale_date_2021-11-05',
 'sale_date_2021-11-06',
 'sale_date_2021-11-07',
 'sale_date_2021-11-08',
 'sale_date_2021-11-09',
 'sale_date_2021-11-10',
 'sale_date_2021-11-11',
 'sale_date_2021-11-12',
 'sale_date_2021-11-13',
 'sale_date_2021-11-14',
 'sale_date_2021-11-15',
 'sale_date_2021-11-16',
 'sale_date_2021-11-17',
 'sale_date_2021-11-18',
 'sale_date_2021-11-19',
 'sale_date_2021-11-20',
 'sale_date_2021-11-21',
 'sale_date_2021-11-22',
 'sale_date_2021-11-23',
 'sale_date_2021-11-24',
 'sale_date_2021-11-25',
 'sale_date_2021-11-26',
 'sale_date_2021-11-27',
 'sale_date_2021-11-28',
 'sale_date_2021-11-29',
 'sale_date_2021-11-30',
 'sale_date_2021-12-01',
 'sale_date_2021-12-02',
 'sale_date_2021-12-03',
 'sale_date_2021-12-04',
 'sale_date_2021-12-05',
 'sale_date_2021-12-06',
 'sale_date_2021-12-07',
 'sale_date_2021-12-08',
 'sale_date_2021-12-09',
 'sale_date_2021-12-10',
 'sale_date_2021-12-11',
 'sale_date_2021-12-12',
 'sale_date_2021-12-13',
 'sale_date_2021-12-14',
 'sale_date_2021-12-15',
 'sale_date_2021-12-16',
 'sale_date_2021-12-17',
 'sale_date_2021-12-18',
 'sale_date_2021-12-19',
 'sale_date_2021-12-20',
 'sale_date_2021-12-21',
 'sale_date_2021-12-22',
 'sale_date_2021-12-23',
 'sale_date_2021-12-24',
 'sale_date_2021-12-25',
 'sale_date_2021-12-26',
 'sale_date_2021-12-27',
 'sale_date_2021-12-28',
 'sale_date_2021-12-29',
 'sale_date_2021-12-30',
 'sale_date_2021-12-31',
 'sale_date_2022-01-01',
 'sale_date_2022-01-02',
 'sale_date_2022-01-03',
 'sale_date_2022-01-04',
 'sale_date_2022-01-05',
 'sale_date_2022-01-06',
 'sale_date_2022-01-07',
 'sale_date_2022-01-08',
 'sale_date_2022-01-09',
 'sale_date_2022-01-10',
 'sale_date_2022-01-11',
 'sale_date_2022-01-12',
 'sale_date_2022-01-13',
 'sale_date_2022-01-14',
 'sale_date_2022-01-15',
 'sale_date_2022-01-16',
 'sale_date_2022-01-17',
 'sale_date_2022-01-18',
 'sale_date_2022-01-19',
 'sale_date_2022-01-20',
 'sale_date_2022-01-21',
 'sale_date_2022-01-22',
 'sale_date_2022-01-23',
 'sale_date_2022-01-24',
 'sale_date_2022-01-25',
 'sale_date_2022-01-26',
 'sale_date_2022-01-27',
 'sale_date_2022-01-28',
 'sale_date_2022-01-29',
 'sale_date_2022-01-30',
 'sale_date_2022-01-31',
 'sale_date_2022-02-01',
 'sale_date_2022-02-02',
 'sale_date_2022-02-03',
 'sale_date_2022-02-04',
 'sale_date_2022-02-05',
 'sale_date_2022-02-06',
 'sale_date_2022-02-07',
 'sale_date_2022-02-08',
 'sale_date_2022-02-09',
 'sale_date_2022-02-10',
 'sale_date_2022-02-11',
 'sale_date_2022-02-12',
 'sale_date_2022-02-13',
 'sale_date_2022-02-14',
 'sale_date_2022-02-15',
 'sale_date_2022-02-16',
 'sale_date_2022-02-17',
 'sale_date_2022-02-18',
 'sale_date_2022-02-19',
 'sale_date_2022-02-20',
 'sale_date_2022-02-21',
 'sale_date_2022-02-22',
 'sale_date_2022-02-23',
 'sale_date_2022-02-24',
 'sale_date_2022-02-25',
 'sale_date_2022-02-26',
 'sale_date_2022-02-27',
 'sale_date_2022-02-28',
 'sale_date_2022-03-01',
 'sale_date_2022-03-02',
 'sale_date_2022-03-03',
 'sale_date_2022-03-04',
 'sale_date_2022-03-05',
 'sale_date_2022-03-06',
 'sale_date_2022-03-07',
 'sale_date_2022-03-08',
 'sale_date_2022-03-09',
 'sale_date_2022-03-10',
 'sale_date_2022-03-11',
 'sale_date_2022-03-12',
 'sale_date_2022-03-13',
 'sale_date_2022-03-14',
 'sale_date_2022-03-15',
 'sale_date_2022-03-16',
 'sale_date_2022-03-17',
 'sale_date_2022-03-18',
 'sale_date_2022-03-19',
 'sale_date_2022-03-20',
 'sale_date_2022-03-21',
 'sale_date_2022-03-22',
 'sale_date_2022-03-23',
 'sale_date_2022-03-24',
 'sale_date_2022-03-25',
 'sale_date_2022-03-26',
 'sale_date_2022-03-27',
 'sale_date_2022-03-28',
 'sale_date_2022-03-29',
 'sale_date_2022-03-30',
 'sale_date_2022-03-31',
 'sale_date_2022-04-01',
 'sale_date_2022-04-02',
 'sale_date_2022-04-03',
 'sale_date_2022-04-04',
 'sale_date_2022-04-05',
 'sale_date_2022-04-06',
 'sale_date_2022-04-07',
 'sale_date_2022-04-08',
 'sale_date_2022-04-09',
 'sale_date_2022-04-10',
 'sale_date_2022-04-11',
 'sale_date_2022-04-12',
 'sale_date_2022-04-13',
 'sale_date_2022-04-14',
 'sale_date_2022-04-15',
 'sale_date_2022-04-16',
 'sale_date_2022-04-17',
 'sale_date_2022-04-18',
 'sale_date_2022-04-19',
 'sale_date_2022-04-20',
 'sale_date_2022-04-21',
 'sale_date_2022-04-22',
 'sale_date_2022-04-23',
 'sale_date_2022-04-24',
 'sale_date_2022-04-25',
 'sale_date_2022-04-26',
 'sale_date_2022-04-27',
 'sale_date_2022-04-28',
 'sale_date_2022-04-29',
 'sale_date_2022-04-30',
 'sale_date_2022-05-01',
 'sale_date_2022-05-02',
 'sale_date_2022-05-03',
 'sale_date_2022-05-04',
 'sale_date_2022-05-05',
 'sale_date_2022-05-06',
 'sale_date_2022-05-07',
 'sale_date_2022-05-08',
 'sale_date_2022-05-09',
 'sale_date_2022-05-10',
 'sale_date_2022-05-11',
 'sale_date_2022-05-12',
 'sale_date_2022-05-13',
 'sale_date_2022-05-14',
 'sale_date_2022-05-15',
 'sale_date_2022-05-16',
 'sale_date_2022-05-17',
 'sale_date_2022-05-18',
 'sale_date_2022-05-19',
 'sale_date_2022-05-20',
 'sale_date_2022-05-21',
 'sale_date_2022-05-22',
 'sale_date_2022-05-23',
 'sale_date_2022-05-24',
 'sale_date_2022-05-25',
 'sale_date_2022-05-26',
 'sale_date_2022-05-27',
 'sale_date_2022-05-28',
 'sale_date_2022-05-29',
 'sale_date_2022-05-30',
 'sale_date_2022-05-31',
 'sale_date_2022-06-01',
 'sale_date_2022-06-02',
 'sale_date_2022-06-03',
 'sale_date_2022-06-04',
 'sale_date_2022-06-05',
 'sale_date_2022-06-06',
 'sale_date_2022-06-07',
 'sale_date_2022-06-08',
 'sale_date_2022-06-09',
 'sale_date_2022-06-10',
 'sale_date_2022-06-11',
 'sale_date_2022-06-12',
 'sale_date_2022-06-13',
 'sale_date_2022-06-14',
 'sale_date_2022-06-15',
 'sale_date_2022-06-16',
 'sale_date_2022-06-17',
 'sale_date_2022-06-18',
 'sale_date_2022-06-19',
 'sale_date_2022-06-20',
 'sale_date_2022-06-21',
 'sale_date_2022-06-22',
 'sale_date_2022-06-23',
 'sale_date_2022-06-24',
 'sale_date_2022-06-25',
 'sale_date_2022-06-26',
 'sale_date_2022-06-27',
 'sale_date_2022-06-28',
 'sale_date_2022-06-29',
 'sale_date_2022-06-30',
 'sale_date_2022-07-01',
 'sale_date_2022-07-02',
 'sale_date_2022-07-03',
 'sale_date_2022-07-04',
 'sale_date_2022-07-05',
 'sale_date_2022-07-06',
 'sale_date_2022-07-07',
 'sale_date_2022-07-08',
 'sale_date_2022-07-09',
 'sale_date_2022-07-10',
 'sale_date_2022-07-11',
 'sale_date_2022-07-12',
 'sale_date_2022-07-13',
 'sale_date_2022-07-14',
 'sale_date_2022-07-15',
 'sale_date_2022-07-16',
 'sale_date_2022-07-17',
 'sale_date_2022-07-18',
 'sale_date_2022-07-19',
 'sale_date_2022-07-20',
 'sale_date_2022-07-21',
 'sale_date_2022-07-22',
 'sale_date_2022-07-23',
 'sale_date_2022-07-24',
 'sale_date_2022-07-25',
 'sale_date_2022-07-26',
 'sale_date_2022-07-27',
 'sale_date_2022-07-28',
 'sale_date_2022-07-29',
 'sale_date_2022-07-30',
 'sale_date_2022-07-31',
 'sale_date_2022-08-01',
 'sale_date_2022-08-02',
 'sale_date_2022-08-03',
 'sale_date_2022-08-04',
 'sale_date_2022-08-05',
 'sale_date_2022-08-06',
 'sale_date_2022-08-07',
 'sale_date_2022-08-08',
 'sale_date_2022-08-09',
 'sale_date_2022-08-10',
 'sale_date_2022-08-11',
 'sale_date_2022-08-12',
 'sale_date_2022-08-13',
 'sale_date_2022-08-14',
 'sale_date_2022-08-15',
 'sale_date_2022-08-16',
 'sale_date_2022-08-17',
 'sale_date_2022-08-18',
 'sale_date_2022-08-19',
 'sale_date_2022-08-20',
 'sale_date_2022-08-21',
 'sale_date_2022-08-22',
 'sale_date_2022-08-23',
 'sale_date_2022-08-24',
 'sale_date_2022-08-25',
 'sale_date_2022-08-26',
 'sale_date_2022-08-27',
 'sale_date_2022-08-28',
 'sale_date_2022-08-29',
 'sale_date_2022-08-30',
 'sale_date_2022-08-31',
 'sale_date_2022-09-01',
 'sale_date_2022-09-02',
 'sale_date_2022-09-03',
 'sale_date_2022-09-04',
 'sale_date_2022-09-05',
 'sale_date_2022-09-06',
 'sale_date_2022-09-07',
 'sale_date_2022-09-08',
 'sale_date_2022-09-09',
 'sale_date_2022-09-10',
 'sale_date_2022-09-11',
 'sale_date_2022-09-12',
 'sale_date_2022-09-13',
 'sale_date_2022-09-14',
 'sale_date_2022-09-15',
 'sale_date_2022-09-16',
 'sale_date_2022-09-17',
 'sale_date_2022-09-18',
 'sale_date_2022-09-19',
 'sale_date_2022-09-20',
 'sale_date_2022-09-21',
 'sale_date_2022-09-22',
 'sale_date_2022-09-23',
 'sale_date_2022-09-24',
 'sale_date_2022-09-25',
 'sale_date_2022-09-26',
 'sale_date_2022-09-27',
 'sale_date_2022-09-28',
 'sale_date_2022-09-29',
 'sale_date_2022-09-30',
 'ad_exp_Display/banner ad',
 "ad_exp_Don't recall seeing an ad",
 'ad_exp_Some other type of ad',
 'ad_exp_Sponsored Brands',
 'ad_exp_Sponsored Products',
 'ad_exp_Video ad',
 'product_brand_Alpha',
 'product_brand_Arf',
 'product_brand_Astro',
 'product_brand_Beam',
 'product_brand_Beethoven',
 'product_brand_Bezt',
 'product_brand_Bones',
 'product_brand_Choice',
 'product_brand_Flora',
 'product_brand_Garland',
 'product_brand_Hanover',
 'product_brand_Health One',
 'product_brand_Hearth',
 'product_brand_K99',
 'product_brand_Kastle',
 'product_brand_King',
 'product_brand_Omaha',
 'product_brand_Paws',
 'product_brand_Perro',
 'product_brand_Playtime',
 'product_brand_Rivera',
 'product_brand_Romero',
 'product_brand_Ruby',
 'product_brand_Seattle Gourmet',
 'product_brand_Top',
 'product_name_Alpha ',
 'product_name_Alpha High Protein Dog Food with Probiotics for Dogs, Shredded Blend Turkey & Rice Formula - 17 lb. Bag',
 'product_name_Alpha Moist & Meaty Steak Flavor Adult Dry Dog Food',
 'product_name_Alpha Natural Adult Beef & Rice Dry Dog Food',
 'product_name_Alpha Natural Adult Chicken & Rice Dry Dog Food',
 'product_name_Alpha Natural Adult Lamb & Rice Dry Dog Food',
 'product_name_Alpha Natural Dry Dog Food, True Instinct With Real Turkey & Venison - 15 lb. Bag',
 'product_name_Alpha Natural Dry Dog Food, True Instinct With Real Turkey & Venison - 7.4 lb. Bag',
 'product_name_Alpha Natural Healthy Weight Formula Adult Dry Dog Food & Wet Dog Food',
 'product_name_Alpha Natural Large Breed Formula Adult Dry Dog Food',
 'product_name_Alpha Natural Sensitive Systems, Skin & Coat Salmon Adult Dry Dog Food',
 'product_name_Alpha Performance - High Protein Dry Dog Food - Chicken & Rice',
 'product_name_Alpha Probiotics Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice',
 'product_name_Alpha Sensitive Skin & Stomach with Oats Adult Dry Dog Food',
 'product_name_Alpha Sensitive Skin & Stomach, High Protein Dry Dog Food',
 'product_name_Alpha Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice (Packagin',
 'product_name_Alpha Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice (Packaging May Vary)',
 'product_name_Alpha ive Skin & Stomach, High Protein Dry Dog Food',
 'product_name_Alpha n, Natural Dry Dog Food, True Instinct With Real Turkey & Venison - 7.4 lb. Bag',
 'product_name_Alpha robiotics Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice',
 'product_name_Arf Dog Food, 35% Protein, No Added Grains (Beef, Salmon, Turkey, Lamb, Chicken)',
 'product_name_Arf Dry Dog Food Large Breed with Grains (Chicken and Brown Rice)',
 'product_name_Arf Jerky Dog Treats, 2 Lb Bag (Chicken, Duck, Sweet Potato Wraps)',
 'product_name_Arf Soft & Tender American Jerky Dog Treats',
 'product_name_Arf Wet Canned Dog Food 12.5/13.2 oz',
 'product_name_Arf Wholesome Grains Adult Healthy Weight Dry Dog Food - Chicken & Brown Rice Recipe',
 'product_name_Arf Wholesome Grains Dry Dog Food (Chicken/Salmon/Beef/Lamb and Brown Rice)',
 'product_name_Arf Wholesome Grains Senior Dry Dog Food - Chicken & Brown Rice Recipe',
 'product_name_Arf lesome Grains Senior Dry Dog Food - Chicken & Brown Rice Recipe',
 'product_name_Astro Grain-Free High-Protein Dry Dog Food, Natural Ingredients, Made in USA with Real Meat, All Breeds,',
 'product_name_Astro Small Breed Dry Dog Food with Grains, Natural Ingredients, Made in USA with Real Turkey, for Dogs U',
 'product_name_Astro ee High-Protein Dry Dog Food, Natural Ingredients, Made in USA with Real Meat, All Breeds, for Adul',
 'product_name_Astro th Small Breed Dry Dog Food with Grains, Natural Ingredients, Made in USA with Real Turkey, for Dog',
 'product_name_Beam Dish Super Premium Dry Dog Food with Real Meat, Veggies & Fruit',
 'product_name_Beam Dry Dog Food, Beef, Pea & Brown Rice Recipe',
 'product_name_Beam Just 6 Limited Ingredient Diet Dry Dog Food',
 'product_name_Beam Premium Natural Dry Dog Food, Real Chicken & Veggies Recipe, 28 Pounds',
 'product_name_Beam emium Natural Dry Dog Food, Real Chicken & Veggies Recipe, 28 Pounds (Packaging May Vary)',
 'product_name_Beam sh Super Premium Dry Dog Food with Real Meat, Veggies & Fruit',
 'product_name_Beam st 6 Limited Ingredient Diet Dry Dog Food',
 'product_name_Beam y Dog Food, Beef, Pea & Brown Rice Recipe',
 'product_name_Beethoven Roasted Bison and Venison High Protein Real Meat Recipes Premium Dry Dog Food with Superfoods and N',
 'product_name_Beethoven Wild Smoke-Flavored Salmon High Protein Recipes Premium Dry Dog Food with Real Salmon, Superfoods',
 'product_name_Beethoven e-Flavored Salmon High Protein Recipes Premium Dry Dog Food with Real Salmon, Superfoods and Nutrie',
 'product_name_Bezt Adult Chicken and Brown Rice Recipe Dry Dog Food',
 'product_name_Bezt High Protein, Natural Adult Dry Dog Food',
 'product_name_Bezt Natural Adult Beef and Brown Rice Dry Dog Food',
 'product_name_Bezt Natural Adult Dry Dog Food',
 'product_name_Bezt Natural Adult Fish and Brown Rice Dry Dog Food',
 'product_name_Bezt Natural Adult Healthy Weight Chicken and Brown Rice Dry Dog Food',
 'product_name_Bezt Natural Adult Large Breed Dry Dog Food',
 'product_name_Bezt Natural Adult Small Breed Dry Dog Food',
 'product_name_Bezt Natural Adult Wet Dog Food, 12.5-oz cans (Pack of 12)',
 'product_name_Bezt Natural Senior Dry Dog Food, Chicken and Brown Rice',
 'product_name_Bezt Natural Senior Wet Dog Food, Chicken 12.5-oz can (Pack of 12)',
 'product_name_Bezt Natural Small Breed Wet Dog Food Cups, in Hearty Gravy, 3.5-oz Cups',
 'product_name_Bezt ection Formula Natural Adult Beef and Brown Rice Dry Dog Food',
 'product_name_Bezt ection Formula Natural Adult Large Breed Dry Dog Food',
 'product_name_Bones Human Grade Dehydrated Whole Grain Dog Food – Complete Meal or Dog Food Topper',
 'product_name_Choice Chopped Ground Dinner Adult Wet Dog Food, 3.5 oz. Pouches',
 'product_name_Choice Cuts in Gravy Adult Wet Dog Food, 3.5 oz. Pouches',
 'product_name_Choice Dry Dog Food',
 'product_name_Choice Small Breed Adult Dry Dog Food, Chicken & Steak',
 'product_name_Choice Small Dog Complete Nutrition Small Breed Adult Dry Dog Food Grilled Steak and Vegetable Flavor Dog',
 'product_name_Choice dult Dry Dog Food, Chicken & Steak',
 'product_name_Flora Kibble Dry Dog Food, 20 lb, with Plant Based Protein',
 'product_name_Garland Classic Healthy Grains Dry Dog Food with Real Meat',
 'product_name_Garland Dog Food Health Weight Recipe',
 'product_name_Garland Food with Real Meat',
 'product_name_Garland Grain Free with Real Meat + Sweet Potato Dry Dog Food',
 'product_name_Garland Healthy Grains Dry Dog Food with Real Meat',
 'product_name_Garland Real Meat Dry Dog Food Health Weight Recipe',
 'product_name_Garland Senior Dry Dog Food with Real Meat',
 'product_name_Garland Small Breed Dry Dog Food with Real Meat',
 'product_name_Garland h Real Meat + Sweet Potato Dry Dog Food',
 'product_name_Garland ll Breed Dry Dog Food with Real Meat',
 'product_name_Garland y Grains Dry Dog Food with Real Meat',
 'product_name_Hanover Original Recipe, 13lb, High-Protein Grain-Free Dry Dog Food',
 'product_name_Health One Adult Dry Dog Food, Chicken Lamb & Salmon Flavor',
 'product_name_Health One Dog Food, Chicken Lamb & Salmon Flavor',
 'product_name_Health One High Protein Natural Dry Dog Food with a Trio of Proteins from Chicken, Lamb and Salmon, 4 lb. Bag',
 'product_name_Health One NATURAL CHOICE Natural Adult & Senior Dry Dog Food for Small & Toy Breeds',
 'product_name_Health One NATURAL CHOICE Natural Adult Dry Dog Food, Chicken',
 'product_name_Health One Natural Choice Small Bites Adult Dry Dog Food, Lamb & Chicken',
 'product_name_Health One Small & Toy Breed Adult Dry Dog Food',
 'product_name_Health One Ultra High Protein Natural Dry Dog Puppy Food with a Trio of Proteins from Chicken Lamb and Salmon',
 'product_name_Health One in Natural Dry Dog Puppy Food with a Trio of Proteins from Chicken Lamb and Salmon, 4 lb. Bag',
 'product_name_Health One y Breed Adult Dry Dog Food',
 'product_name_Hearth Grain-Free Dry Dog Food, Humanely Raised Meat Recipe with Non-GMO Superfoods and No Artificial Flav',
 'product_name_Hearth ry Dog Food, Humanely Raised Meat Recipe with Non-GMO Superfoods and No Artificial Flavors or Prese',
 'product_name_K99 Super Premium Dog Food – Professional Dry Dog Food – Super Premium Dog Food with 26% Protein, Glute',
 'product_name_K99 og Food – Professional Dry Dog Food – Super Premium Dog Food with 26% Protein, Gluten Free - for Hi',
 'product_name_Kastle Original Savory Beef & Chicken Dry Dog Food',
 'product_name_King Dry Puppy Food',
 'product_name_King Health Nutrition Medium Adult Dry Dog Food',
 'product_name_King Health Nutrition Small Adult Dry Dog Food',
 'product_name_King th Nutrition French Bulldog Dry Puppy Food',
 'product_name_Omaha Natural Dry Dog Food, Raw Coated Whole Grain Dog Food',
 'product_name_Omaha y Dog Food, Raw Coated Whole Grain Dog Food',
 'product_name_Paws Adult Dry Dog Food for Healthy Weight, Chicken',
 'product_name_Paws Dry Dog Food, Chicken & Lamb',
 'product_name_Paws Large Breed Adult Dry Dog Food, Chicken & Lamb',
 'product_name_Paws Minichunks Adult Dry Dog Food, Chicken',
 'product_name_Paws d for Healthy Weight, Chicken',
 'product_name_Perro Complete Turkey & Salmon Recipe Senior Grain-Free Freeze-Dried Raw Dog Food',
 'product_name_Playtime Limited Ingredient Formula Grain-Free Dry Dog Food',
 'product_name_Playtime edient Formula Grain-Free Dry Dog Food',
 'product_name_Rivera High Protein Adult Dry Dog Food, Wholesome Grains and Grain Free',
 'product_name_Rivera lt Dry Dog Food, Wholesome Grains and Grain Free',
 'product_name_Romero Food Variety Packs – 24 Trays',
 'product_name_Romero Gourmet Wet Dog Food Variety Packs – 24 Trays',
 'product_name_Romero Soft Wet Dog Food Pot Roast & Vegetable, Beef Stew, Turkey Potato & Green Bean, and Hearth Chicken',
 'product_name_Romero ft Wet Dog Food Pot Roast & Vegetable, Beef Stew, Turkey Potato & Green Bean, and Hearth Chicken &',
 'product_name_Ruby & Coat Real Fish Recipe Dry Dog Food with Protein, and Probiotics',
 'product_name_Ruby Dry Senior Dog Food Formula High Quality With Protein, Probiotics, Superfoods, And Antioxidants',
 'product_name_Ruby Premium Formulas Dry Dog Food for Adult Dogs Made with Real Meat Protein, Superfoods, Probiotics and Antioxidants for Su',
 'product_name_Ruby Skin & Coat Real Fish Recipe Dry Dog Food with Protein, and Probiotics',
 'product_name_Seattle Gourmet Adult 7+ Small Bites Chicken Meal, Barley & Brown Rice Recipe Dry Dog Food, 15 lb. Bag',
 'product_name_Seattle Gourmet Dry Dog Food, Adult 1-5, Large Breed',
 'product_name_Seattle Gourmet Dry Dog Food, Adult 1-6',
 'product_name_Seattle Gourmet Dry Dog Food, Adult, Large Breed, Light, Chicken Meal & Barley Recipe',
 'product_name_Seattle Gourmet Dry Dog Food, Adult, Sensitive Stomach & Skin Recipes',
 'product_name_Seattle Gourmet Dry Dog Food, Adult, Small Paws for Small Breed Dogs',
 'product_name_Seattle Gourmet y Dog Food, Adult 1-5, Large Breed',
 'product_name_Seattle Gourmet y Dog Food, Adult 1-6',
 'product_name_Seattle Gourmet y Dog Food, Adult, Large Breed, Light, Chicken Meal & Barley Recipe for Healthy Weight & Weight Man',
 'product_name_Seattle Gourmet y Dog Food, Adult, Sensitive Stomach & Skin Recipes',
 'product_name_Seattle Gourmet y Dog Food, Adult, Small Paws for Small Breed Dogs',
 'product_name_Top Adult Dry Dog Food',
 'product_name_Top Bites Dry Dog Food, Chicken & Rice Recipe, 4 Pound Bag',
 'product_name_Top Dry Dog Food',
 'product_name_Top Grain-Free Salmon, Sweet Potato & Pumpkin Dry Dog Food',
 'product_name_Top Limited Ingredient Diet | Adult Grain-Free Dry Dog Food',
 'product_name_Top Small Bites Dry Dog Food, Chicken & Rice Recipe, 4 Pound Bag',
 'gender_F',
 'gender_M',
 'city_Abilene',
 'city_Aiken',
 'city_Akron',
 'city_Albany',
 'city_Albuquerque',
 'city_Alexandria',
 'city_Allentown',
 'city_Alpharetta',
 'city_Amarillo',
 'city_Anaheim',
 'city_Anchorage',
 'city_Anderson',
 'city_Ann Arbor',
 'city_Annapolis',
 'city_Anniston',
 'city_Apache Junction',
 'city_Appleton',
 'city_Arlington',
 'city_Arvada',
 'city_Ashburn',
 'city_Asheville',
 'city_Athens',
 'city_Atlanta',
 'city_Augusta',
 'city_Aurora',
 'city_Austin',
 'city_Bakersfield',
 'city_Baltimore',
 'city_Baton Rouge',
 'city_Battle Creek',
 'city_Beaufort',
 'city_Beaumont',
 'city_Bellevue',
 'city_Berkeley',
 'city_Bethesda',
 'city_Bethlehem',
 'city_Billings',
 'city_Biloxi',
 'city_Birmingham',
 'city_Bismarck',
 'city_Bloomington',
 'city_Boca Raton',
 'city_Boise',
 'city_Bonita Springs',
 'city_Boston',
 'city_Boulder',
 'city_Boynton Beach',
 'city_Bozeman',
 'city_Bradenton',
 'city_Brea',
 'city_Bridgeport',
 'city_Brockton',
 'city_Bronx',
 'city_Brooklyn',
 'city_Bryan',
 'city_Buffalo',
 'city_Burbank',
 'city_Cambridge',
 'city_Camden',
 'city_Canton',
 'city_Carlsbad',
 'city_Carol Stream',
 'city_Carson City',
 'city_Cedar Rapids',
 'city_Champaign',
 'city_Charleston',
 'city_Charlotte',
 'city_Charlottesville',
 'city_Chattanooga',
 'city_Chesapeake',
 'city_Cheyenne',
 'city_Chicago',
 'city_Chico',
 'city_Chula Vista',
 'city_Cincinnati',
 'city_Clearwater',
 'city_Cleveland',
 'city_College Station',
 'city_Colorado Springs',
 'city_Columbia',
 'city_Columbus',
 'city_Concord',
 'city_Conroe',
 'city_Corona',
 'city_Corpus Christi',
 'city_Cumming',
 'city_Dallas',
 'city_Danbury',
 'city_Davenport',
 'city_Dayton',
 'city_Daytona Beach',
 'city_Dearborn',
 'city_Decatur',
 'city_Delray Beach',
 'city_Denton',
 'city_Denver',
 'city_Des Moines',
 'city_Detroit',
 'city_Dulles',
 'city_Duluth',
 'city_Durham',
 'city_East Saint Louis',
 'city_Edmond',
 'city_El Paso',
 'city_Elizabeth',
 'city_Elmira',
 'city_Erie',
 'city_Escondido',
 'city_Eugene',
 'city_Evanston',
 'city_Evansville',
 'city_Everett',
 'city_Fairbanks',
 'city_Fairfax',
 'city_Fairfield',
 'city_Falls Church',
 'city_Fargo',
 'city_Farmington',
 'city_Fayetteville',
 'city_Flint',
 'city_Florence',
 'city_Flushing',
 'city_Fort Collins',
 'city_Fort Lauderdale',
 'city_Fort Myers',
 'city_Fort Pierce',
 'city_Fort Smith',
 'city_Fort Wayne',
 'city_Fort Worth',
 'city_Frankfort',
 'city_Frederick',
 'city_Fredericksburg',
 'city_Fresno',
 'city_Fullerton',
 'city_Gadsden',
 'city_Gainesville',
 'city_Gaithersburg',
 'city_Galveston',
 'city_Garden Grove',
 'city_Garland',
 'city_Gary',
 'city_Gatesville',
 'city_Gilbert',
 'city_Glendale',
 'city_Grand Forks',
 'city_Grand Junction',
 'city_Grand Rapids',
 'city_Great Neck',
 'city_Greeley',
 'city_Green Bay',
 'city_Greensboro',
 'city_Greenville',
 'city_Gulfport',
 'city_Hagerstown',
 'city_Hamilton',
 'city_Hampton',
 'city_Harrisburg',
 'city_Hartford',
 'city_Hattiesburg',
 'city_Hayward',
 'city_Helena',
 'city_Henderson',
 'city_Herndon',
 'city_Hialeah',
 'city_Hicksville',
 'city_High Point',
 'city_Hollywood',
 'city_Honolulu',
 'city_Hot Springs National Park',
 'city_Houston',
 'city_Humble',
 'city_Huntington',
 'city_Huntington Beach',
 'city_Huntsville',
 'city_Hyattsville',
 'city_Idaho Falls',
 'city_Independence',
 'city_Indianapolis',
 'city_Inglewood',
 'city_Iowa City',
 'city_Irvine',
 'city_Irving',
 'city_Jackson',
 'city_Jacksonville',
 'city_Jamaica',
 'city_Jefferson City',
 'city_Jeffersonville',
 'city_Jersey City',
 'city_Johnson City',
 'city_Johnstown',
 'city_Joliet',
 'city_Juneau',
 'city_Kalamazoo',
 'city_Kansas City',
 'city_Katy',
 'city_Killeen',
 'city_Kingsport',
 'city_Kissimmee',
 'city_Knoxville',
 'city_Lafayette',
 'city_Lake Charles',
 'city_Lake Worth',
 'city_Lakeland',
 'city_Lakewood',
 'city_Lancaster',
 'city_Lansing',
 'city_Laredo',
 'city_Largo',
 'city_Las Cruces',
 'city_Las Vegas',
 'city_Laurel',
 'city_Lawrenceville',
 'city_Lees Summit',
 'city_Lehigh Acres',
 'city_Levittown',
 'city_Lexington',
 'city_Lima',
 'city_Lincoln',
 'city_Little Rock',
 'city_Littleton',
 'city_London',
 'city_Long Beach',
 'city_Longview',
 'city_Loretto',
 'city_Los Angeles',
 'city_Louisville',
 'city_Lubbock',
 'city_Lynchburg',
 'city_Lynn',
 'city_Macon',
 'city_Madison',
 'city_Manassas',
 'city_Manchester',
 'city_Mansfield',
 'city_Maple Plain',
 'city_Marietta',
 'city_Melbourne',
 'city_Memphis',
 'city_Meridian',
 'city_Mesa',
 'city_Mesquite',
 'city_Metairie',
 'city_Miami',
 'city_Midland',
 'city_Migrate',
 'city_Milwaukee',
 'city_Minneapolis',
 'city_Missoula',
 'city_Mobile',
 'city_Modesto',
 'city_Monroe',
 'city_Montgomery',
 'city_Monticello',
 'city_Montpelier',
 'city_Moreno Valley',
 'city_Mountain View',
 'city_Muncie',
 'city_Murfreesboro',
 'city_Muskegon',
 'city_Myrtle Beach',
 'city_Naperville',
 'city_Naples',
 'city_Nashville',
 'city_New Brunswick',
 'city_New Castle',
 'city_New Haven',
 'city_New Hyde Park',
 'city_New Orleans',
 'city_New York City',
 'city_Newark',
 'city_Newport News',
 'city_Newton',
 'city_Norcross',
 'city_Norfolk',
 'city_Norman',
 'city_North Hollywood',
 'city_North Las Vegas',
 'city_North Little Rock',
 'city_North Port',
 'city_Northridge',
 'city_Norwalk',
 'city_Oakland',
 'city_Ocala',
 'city_Odessa',
 'city_Ogden',
 'city_Oklahoma City',
 'city_Olympia',
 'city_Omaha',
 'city_Orange',
 'city_Orlando',
 'city_Oxnard',
 'city_Palatine',
 'city_Palmdale',
 'city_Palo Alto',
 'city_Panama City',
 'city_Pasadena',
 'city_Paterson',
 'city_Pensacola',
 'city_Peoria',
 'city_Petaluma',
 'city_Philadelphia',
 'city_Phoenix',
 'city_Pinellas Park',
 'city_Pittsburgh',
 'city_Pocatello',
 'city_Pomona',
 'city_Pompano Beach',
 'city_Port Charlotte',
 'city_Port Saint Lucie',
 'city_Port Washington',
 'city_Portland',
 'city_Portsmouth',
 'city_Prescott',
 'city_Providence',
 'city_Provo',
 'city_Pueblo',
 'city_Punta Gorda',
 'city_Racine',
 'city_Raleigh',
 'city_Reading',
 'city_Redwood City',
 'city_Reno',
 'city_Reston',
 'city_Richmond',
 'city_Ridgely',
 'city_Riverside',
 'city_Roanoke',
 'city_Rochester',
 'city_Rockford',
 'city_Rockville',
 'city_Round Rock',
 'city_Sacramento',
 'city_Saginaw',
 'city_Saint Augustine',
 'city_Saint Cloud',
 'city_Saint Joseph',
 'city_Saint Louis',
 'city_Saint Paul',
 'city_Saint Petersburg',
 'city_Salem',
 'city_Salinas',
 'city_Salt Lake City',
 'city_San Angelo',
 'city_San Antonio',
 'city_San Bernardino',
 'city_San Diego',
 'city_San Francisco',
 'city_San Jose',
 'city_San Luis Obispo',
 'city_San Rafael',
 'city_Sandy',
 'city_Santa Ana',
 'city_Santa Barbara',
 'city_Santa Clara',
 'city_Santa Fe',
 'city_Santa Monica',
 'city_Santa Rosa',
 'city_Sarasota',
 'city_Savannah',
 'city_Schaumburg',
 'city_Scottsdale',
 'city_Scranton',
 'city_Seattle',
 'city_Seminole',
 'city_Shawnee Mission',
 'city_Shreveport',
 'city_Silver Spring',
 'city_Simi Valley',
 'city_Sioux City',
 'city_Sioux Falls',
 'city_South Bend',
 'city_South Lake Tahoe',
 'city_Southfield',
 'city_Sparks',
 'city_Spartanburg',
 'city_Spokane',
 'city_Spring',
 'city_Spring Hill',
 'city_Springfield',
 'city_Stamford',
 'city_Staten Island',
 'city_Sterling',
 'city_Stockton',
 'city_Suffolk',
 'city_Sunnyvale',
 'city_Syracuse',
 'city_Tacoma',
 'city_Tallahassee',
 'city_Tampa',
 'city_Tempe',
 'city_Temple',
 'city_Terre Haute',
 'city_Texarkana',
 'city_Toledo',
 'city_Topeka',
 'city_Torrance',
 'city_Trenton',
 'city_Troy',
 'city_Tucson',
 'city_Tulsa',
 'city_Tuscaloosa',
 'city_Tyler',
 'city_Utica',
 'city_Valdosta',
 'city_Valley Forge',
 'city_Van Nuys',
 'city_Vancouver',
 'city_Ventura',
 'city_Vero Beach',
 'city_Vienna',
 'city_Virginia Beach',
 'city_Visalia',
 'city_Waco',
 'city_Waltham',
 'city_Warren',
 'city_Washington',
 'city_Waterbury',
 'city_Waterloo',
 'city_West Hartford',
 'city_West Palm Beach',
 'city_White Plains',
 'city_Whittier',
 'city_Wichita',
 'city_Wichita Falls',
 'city_Wilkes Barre',
 'city_Wilmington',
 'city_Winston Salem',
 'city_Winter Haven',
 'city_Woburn',
 'city_Worcester',
 'city_Yakima',
 'city_Yonkers',
 'city_York',
 'city_Young America',
 'city_Youngstown',
 'city_Zephyrhills',
 'st_AK',
 'st_AL',
 'st_AR',
 'st_AZ',
 'st_CA',
 'st_CO',
 'st_CT',
 'st_DC',
 'st_DE',
 'st_FL',
 'st_GA',
 'st_HI',
 'st_IA',
 'st_ID',
 'st_IL',
 'st_IN',
 'st_KS',
 'st_KY',
 'st_LA',
 'st_MA',
 'st_MD',
 'st_MI',
 'st_MN',
 'st_MO',
 'st_MS',
 ...]


reversed_list = column_list[::-1]
reversed_list

['age_65+',
 'age_55-64',
 'age_45-54',
 'age_35-44',
 'age_25-34',
 'age_18-24',
 'income_Less than $20,000',
 'income_$80,000 - $99,999',
 'income_$60,000 - $79,999',
 'income_$40,000 - $59,999',
 'income_$20,000 - $39,999',
 'income_$100,000 or more',
 'education_Some college or trade school',
 'education_Post graduate',
 'education_High school graduate',
 'education_College graduate',
 'marital_Single',
 'marital_Married',
 'marital_Domestic partner/serious relationship',
 'st_WY',
 'st_WV',
 'st_WI',
 'st_WA',
 'st_VT',
 'st_VA',
 'st_UT',
 'st_TX',
 'st_TN',
 'st_SD',
 'st_SC',
 'st_RI',
 'st_PA',
 'st_OR',
 'st_OK',
 'st_OH',
 'st_NY',
 'st_NV',
 'st_NM',
 'st_NJ',
 'st_NH',
 'st_NE',
 'st_ND',
 'st_NC',
 'st_MT',
 'st_MS',
 'st_MO',
 'st_MN',
 'st_MI',
 'st_MD',
 'st_MA',
 'st_LA',
 'st_KY',
 'st_KS',
 'st_IN',
 'st_IL',
 'st_ID',
 'st_IA',
 'st_HI',
 'st_GA',
 'st_FL',
 'st_DE',
 'st_DC',
 'st_CT',
 'st_CO',
 'st_CA',
 'st_AZ',
 'st_AR',
 'st_AL',
 'st_AK',
 'city_Zephyrhills',
 'city_Youngstown',
 'city_Young America',
 'city_York',
 'city_Yonkers',
 'city_Yakima',
 'city_Worcester',
 'city_Woburn',
 'city_Winter Haven',
 'city_Winston Salem',
 'city_Wilmington',
 'city_Wilkes Barre',
 'city_Wichita Falls',
 'city_Wichita',
 'city_Whittier',
 'city_White Plains',
 'city_West Palm Beach',
 'city_West Hartford',
 'city_Waterloo',
 'city_Waterbury',
 'city_Washington',
 'city_Warren',
 'city_Waltham',
 'city_Waco',
 'city_Visalia',
 'city_Virginia Beach',
 'city_Vienna',
 'city_Vero Beach',
 'city_Ventura',
 'city_Vancouver',
 'city_Van Nuys',
 'city_Valley Forge',
 'city_Valdosta',
 'city_Utica',
 'city_Tyler',
 'city_Tuscaloosa',
 'city_Tulsa',
 'city_Tucson',
 'city_Troy',
 'city_Trenton',
 'city_Torrance',
 'city_Topeka',
 'city_Toledo',
 'city_Texarkana',
 'city_Terre Haute',
 'city_Temple',
 'city_Tempe',
 'city_Tampa',
 'city_Tallahassee',
 'city_Tacoma',
 'city_Syracuse',
 'city_Sunnyvale',
 'city_Suffolk',
 'city_Stockton',
 'city_Sterling',
 'city_Staten Island',
 'city_Stamford',
 'city_Springfield',
 'city_Spring Hill',
 'city_Spring',
 'city_Spokane',
 'city_Spartanburg',
 'city_Sparks',
 'city_Southfield',
 'city_South Lake Tahoe',
 'city_South Bend',
 'city_Sioux Falls',
 'city_Sioux City',
 'city_Simi Valley',
 'city_Silver Spring',
 'city_Shreveport',
 'city_Shawnee Mission',
 'city_Seminole',
 'city_Seattle',
 'city_Scranton',
 'city_Scottsdale',
 'city_Schaumburg',
 'city_Savannah',
 'city_Sarasota',
 'city_Santa Rosa',
 'city_Santa Monica',
 'city_Santa Fe',
 'city_Santa Clara',
 'city_Santa Barbara',
 'city_Santa Ana',
 'city_Sandy',
 'city_San Rafael',
 'city_San Luis Obispo',
 'city_San Jose',
 'city_San Francisco',
 'city_San Diego',
 'city_San Bernardino',
 'city_San Antonio',
 'city_San Angelo',
 'city_Salt Lake City',
 'city_Salinas',
 'city_Salem',
 'city_Saint Petersburg',
 'city_Saint Paul',
 'city_Saint Louis',
 'city_Saint Joseph',
 'city_Saint Cloud',
 'city_Saint Augustine',
 'city_Saginaw',
 'city_Sacramento',
 'city_Round Rock',
 'city_Rockville',
 'city_Rockford',
 'city_Rochester',
 'city_Roanoke',
 'city_Riverside',
 'city_Ridgely',
 'city_Richmond',
 'city_Reston',
 'city_Reno',
 'city_Redwood City',
 'city_Reading',
 'city_Raleigh',
 'city_Racine',
 'city_Punta Gorda',
 'city_Pueblo',
 'city_Provo',
 'city_Providence',
 'city_Prescott',
 'city_Portsmouth',
 'city_Portland',
 'city_Port Washington',
 'city_Port Saint Lucie',
 'city_Port Charlotte',
 'city_Pompano Beach',
 'city_Pomona',
 'city_Pocatello',
 'city_Pittsburgh',
 'city_Pinellas Park',
 'city_Phoenix',
 'city_Philadelphia',
 'city_Petaluma',
 'city_Peoria',
 'city_Pensacola',
 'city_Paterson',
 'city_Pasadena',
 'city_Panama City',
 'city_Palo Alto',
 'city_Palmdale',
 'city_Palatine',
 'city_Oxnard',
 'city_Orlando',
 'city_Orange',
 'city_Omaha',
 'city_Olympia',
 'city_Oklahoma City',
 'city_Ogden',
 'city_Odessa',
 'city_Ocala',
 'city_Oakland',
 'city_Norwalk',
 'city_Northridge',
 'city_North Port',
 'city_North Little Rock',
 'city_North Las Vegas',
 'city_North Hollywood',
 'city_Norman',
 'city_Norfolk',
 'city_Norcross',
 'city_Newton',
 'city_Newport News',
 'city_Newark',
 'city_New York City',
 'city_New Orleans',
 'city_New Hyde Park',
 'city_New Haven',
 'city_New Castle',
 'city_New Brunswick',
 'city_Nashville',
 'city_Naples',
 'city_Naperville',
 'city_Myrtle Beach',
 'city_Muskegon',
 'city_Murfreesboro',
 'city_Muncie',
 'city_Mountain View',
 'city_Moreno Valley',
 'city_Montpelier',
 'city_Monticello',
 'city_Montgomery',
 'city_Monroe',
 'city_Modesto',
 'city_Mobile',
 'city_Missoula',
 'city_Minneapolis',
 'city_Milwaukee',
 'city_Migrate',
 'city_Midland',
 'city_Miami',
 'city_Metairie',
 'city_Mesquite',
 'city_Mesa',
 'city_Meridian',
 'city_Memphis',
 'city_Melbourne',
 'city_Marietta',
 'city_Maple Plain',
 'city_Mansfield',
 'city_Manchester',
 'city_Manassas',
 'city_Madison',
 'city_Macon',
 'city_Lynn',
 'city_Lynchburg',
 'city_Lubbock',
 'city_Louisville',
 'city_Los Angeles',
 'city_Loretto',
 'city_Longview',
 'city_Long Beach',
 'city_London',
 'city_Littleton',
 'city_Little Rock',
 'city_Lincoln',
 'city_Lima',
 'city_Lexington',
 'city_Levittown',
 'city_Lehigh Acres',
 'city_Lees Summit',
 'city_Lawrenceville',
 'city_Laurel',
 'city_Las Vegas',
 'city_Las Cruces',
 'city_Largo',
 'city_Laredo',
 'city_Lansing',
 'city_Lancaster',
 'city_Lakewood',
 'city_Lakeland',
 'city_Lake Worth',
 'city_Lake Charles',
 'city_Lafayette',
 'city_Knoxville',
 'city_Kissimmee',
 'city_Kingsport',
 'city_Killeen',
 'city_Katy',
 'city_Kansas City',
 'city_Kalamazoo',
 'city_Juneau',
 'city_Joliet',
 'city_Johnstown',
 'city_Johnson City',
 'city_Jersey City',
 'city_Jeffersonville',
 'city_Jefferson City',
 'city_Jamaica',
 'city_Jacksonville',
 'city_Jackson',
 'city_Irving',
 'city_Irvine',
 'city_Iowa City',
 'city_Inglewood',
 'city_Indianapolis',
 'city_Independence',
 'city_Idaho Falls',
 'city_Hyattsville',
 'city_Huntsville',
 'city_Huntington Beach',
 'city_Huntington',
 'city_Humble',
 'city_Houston',
 'city_Hot Springs National Park',
 'city_Honolulu',
 'city_Hollywood',
 'city_High Point',
 'city_Hicksville',
 'city_Hialeah',
 'city_Herndon',
 'city_Henderson',
 'city_Helena',
 'city_Hayward',
 'city_Hattiesburg',
 'city_Hartford',
 'city_Harrisburg',
 'city_Hampton',
 'city_Hamilton',
 'city_Hagerstown',
 'city_Gulfport',
 'city_Greenville',
 'city_Greensboro',
 'city_Green Bay',
 'city_Greeley',
 'city_Great Neck',
 'city_Grand Rapids',
 'city_Grand Junction',
 'city_Grand Forks',
 'city_Glendale',
 'city_Gilbert',
 'city_Gatesville',
 'city_Gary',
 'city_Garland',
 'city_Garden Grove',
 'city_Galveston',
 'city_Gaithersburg',
 'city_Gainesville',
 'city_Gadsden',
 'city_Fullerton',
 'city_Fresno',
 'city_Fredericksburg',
 'city_Frederick',
 'city_Frankfort',
 'city_Fort Worth',
 'city_Fort Wayne',
 'city_Fort Smith',
 'city_Fort Pierce',
 'city_Fort Myers',
 'city_Fort Lauderdale',
 'city_Fort Collins',
 'city_Flushing',
 'city_Florence',
 'city_Flint',
 'city_Fayetteville',
 'city_Farmington',
 'city_Fargo',
 'city_Falls Church',
 'city_Fairfield',
 'city_Fairfax',
 'city_Fairbanks',
 'city_Everett',
 'city_Evansville',
 'city_Evanston',
 'city_Eugene',
 'city_Escondido',
 'city_Erie',
 'city_Elmira',
 'city_Elizabeth',
 'city_El Paso',
 'city_Edmond',
 'city_East Saint Louis',
 'city_Durham',
 'city_Duluth',
 'city_Dulles',
 'city_Detroit',
 'city_Des Moines',
 'city_Denver',
 'city_Denton',
 'city_Delray Beach',
 'city_Decatur',
 'city_Dearborn',
 'city_Daytona Beach',
 'city_Dayton',
 'city_Davenport',
 'city_Danbury',
 'city_Dallas',
 'city_Cumming',
 'city_Corpus Christi',
 'city_Corona',
 'city_Conroe',
 'city_Concord',
 'city_Columbus',
 'city_Columbia',
 'city_Colorado Springs',
 'city_College Station',
 'city_Cleveland',
 'city_Clearwater',
 'city_Cincinnati',
 'city_Chula Vista',
 'city_Chico',
 'city_Chicago',
 'city_Cheyenne',
 'city_Chesapeake',
 'city_Chattanooga',
 'city_Charlottesville',
 'city_Charlotte',
 'city_Charleston',
 'city_Champaign',
 'city_Cedar Rapids',
 'city_Carson City',
 'city_Carol Stream',
 'city_Carlsbad',
 'city_Canton',
 'city_Camden',
 'city_Cambridge',
 'city_Burbank',
 'city_Buffalo',
 'city_Bryan',
 'city_Brooklyn',
 'city_Bronx',
 'city_Brockton',
 'city_Bridgeport',
 'city_Brea',
 'city_Bradenton',
 'city_Bozeman',
 'city_Boynton Beach',
 'city_Boulder',
 'city_Boston',
 'city_Bonita Springs',
 'city_Boise',
 'city_Boca Raton',
 'city_Bloomington',
 'city_Bismarck',
 'city_Birmingham',
 'city_Biloxi',
 'city_Billings',
 'city_Bethlehem',
 'city_Bethesda',
 'city_Berkeley',
 'city_Bellevue',
 'city_Beaumont',
 'city_Beaufort',
 'city_Battle Creek',
 'city_Baton Rouge',
 'city_Baltimore',
 'city_Bakersfield',
 'city_Austin',
 'city_Aurora',
 'city_Augusta',
 'city_Atlanta',
 'city_Athens',
 'city_Asheville',
 'city_Ashburn',
 'city_Arvada',
 'city_Arlington',
 'city_Appleton',
 'city_Apache Junction',
 'city_Anniston',
 'city_Annapolis',
 'city_Ann Arbor',
 'city_Anderson',
 'city_Anchorage',
 'city_Anaheim',
 'city_Amarillo',
 'city_Alpharetta',
 'city_Allentown',
 'city_Alexandria',
 'city_Albuquerque',
 'city_Albany',
 'city_Akron',
 'city_Aiken',
 'city_Abilene',
 'gender_M',
 'gender_F',
 'product_name_Top Small Bites Dry Dog Food, Chicken & Rice Recipe, 4 Pound Bag',
 'product_name_Top Limited Ingredient Diet | Adult Grain-Free Dry Dog Food',
 'product_name_Top Grain-Free Salmon, Sweet Potato & Pumpkin Dry Dog Food',
 'product_name_Top Dry Dog Food',
 'product_name_Top Bites Dry Dog Food, Chicken & Rice Recipe, 4 Pound Bag',
 'product_name_Top Adult Dry Dog Food',
 'product_name_Seattle Gourmet y Dog Food, Adult, Small Paws for Small Breed Dogs',
 'product_name_Seattle Gourmet y Dog Food, Adult, Sensitive Stomach & Skin Recipes',
 'product_name_Seattle Gourmet y Dog Food, Adult, Large Breed, Light, Chicken Meal & Barley Recipe for Healthy Weight & Weight Man',
 'product_name_Seattle Gourmet y Dog Food, Adult 1-6',
 'product_name_Seattle Gourmet y Dog Food, Adult 1-5, Large Breed',
 'product_name_Seattle Gourmet Dry Dog Food, Adult, Small Paws for Small Breed Dogs',
 'product_name_Seattle Gourmet Dry Dog Food, Adult, Sensitive Stomach & Skin Recipes',
 'product_name_Seattle Gourmet Dry Dog Food, Adult, Large Breed, Light, Chicken Meal & Barley Recipe',
 'product_name_Seattle Gourmet Dry Dog Food, Adult 1-6',
 'product_name_Seattle Gourmet Dry Dog Food, Adult 1-5, Large Breed',
 'product_name_Seattle Gourmet Adult 7+ Small Bites Chicken Meal, Barley & Brown Rice Recipe Dry Dog Food, 15 lb. Bag',
 'product_name_Ruby Skin & Coat Real Fish Recipe Dry Dog Food with Protein, and Probiotics',
 'product_name_Ruby Premium Formulas Dry Dog Food for Adult Dogs Made with Real Meat Protein, Superfoods, Probiotics and Antioxidants for Su',
 'product_name_Ruby Dry Senior Dog Food Formula High Quality With Protein, Probiotics, Superfoods, And Antioxidants',
 'product_name_Ruby & Coat Real Fish Recipe Dry Dog Food with Protein, and Probiotics',
 'product_name_Romero ft Wet Dog Food Pot Roast & Vegetable, Beef Stew, Turkey Potato & Green Bean, and Hearth Chicken &',
 'product_name_Romero Soft Wet Dog Food Pot Roast & Vegetable, Beef Stew, Turkey Potato & Green Bean, and Hearth Chicken',
 'product_name_Romero Gourmet Wet Dog Food Variety Packs – 24 Trays',
 'product_name_Romero Food Variety Packs – 24 Trays',
 'product_name_Rivera lt Dry Dog Food, Wholesome Grains and Grain Free',
 'product_name_Rivera High Protein Adult Dry Dog Food, Wholesome Grains and Grain Free',
 'product_name_Playtime edient Formula Grain-Free Dry Dog Food',
 'product_name_Playtime Limited Ingredient Formula Grain-Free Dry Dog Food',
 'product_name_Perro Complete Turkey & Salmon Recipe Senior Grain-Free Freeze-Dried Raw Dog Food',
 'product_name_Paws d for Healthy Weight, Chicken',
 'product_name_Paws Minichunks Adult Dry Dog Food, Chicken',
 'product_name_Paws Large Breed Adult Dry Dog Food, Chicken & Lamb',
 'product_name_Paws Dry Dog Food, Chicken & Lamb',
 'product_name_Paws Adult Dry Dog Food for Healthy Weight, Chicken',
 'product_name_Omaha y Dog Food, Raw Coated Whole Grain Dog Food',
 'product_name_Omaha Natural Dry Dog Food, Raw Coated Whole Grain Dog Food',
 'product_name_King th Nutrition French Bulldog Dry Puppy Food',
 'product_name_King Health Nutrition Small Adult Dry Dog Food',
 'product_name_King Health Nutrition Medium Adult Dry Dog Food',
 'product_name_King Dry Puppy Food',
 'product_name_Kastle Original Savory Beef & Chicken Dry Dog Food',
 'product_name_K99 og Food – Professional Dry Dog Food – Super Premium Dog Food with 26% Protein, Gluten Free - for Hi',
 'product_name_K99 Super Premium Dog Food – Professional Dry Dog Food – Super Premium Dog Food with 26% Protein, Glute',
 'product_name_Hearth ry Dog Food, Humanely Raised Meat Recipe with Non-GMO Superfoods and No Artificial Flavors or Prese',
 'product_name_Hearth Grain-Free Dry Dog Food, Humanely Raised Meat Recipe with Non-GMO Superfoods and No Artificial Flav',
 'product_name_Health One y Breed Adult Dry Dog Food',
 'product_name_Health One in Natural Dry Dog Puppy Food with a Trio of Proteins from Chicken Lamb and Salmon, 4 lb. Bag',
 'product_name_Health One Ultra High Protein Natural Dry Dog Puppy Food with a Trio of Proteins from Chicken Lamb and Salmon',
 'product_name_Health One Small & Toy Breed Adult Dry Dog Food',
 'product_name_Health One Natural Choice Small Bites Adult Dry Dog Food, Lamb & Chicken',
 'product_name_Health One NATURAL CHOICE Natural Adult Dry Dog Food, Chicken',
 'product_name_Health One NATURAL CHOICE Natural Adult & Senior Dry Dog Food for Small & Toy Breeds',
 'product_name_Health One High Protein Natural Dry Dog Food with a Trio of Proteins from Chicken, Lamb and Salmon, 4 lb. Bag',
 'product_name_Health One Dog Food, Chicken Lamb & Salmon Flavor',
 'product_name_Health One Adult Dry Dog Food, Chicken Lamb & Salmon Flavor',
 'product_name_Hanover Original Recipe, 13lb, High-Protein Grain-Free Dry Dog Food',
 'product_name_Garland y Grains Dry Dog Food with Real Meat',
 'product_name_Garland ll Breed Dry Dog Food with Real Meat',
 'product_name_Garland h Real Meat + Sweet Potato Dry Dog Food',
 'product_name_Garland Small Breed Dry Dog Food with Real Meat',
 'product_name_Garland Senior Dry Dog Food with Real Meat',
 'product_name_Garland Real Meat Dry Dog Food Health Weight Recipe',
 'product_name_Garland Healthy Grains Dry Dog Food with Real Meat',
 'product_name_Garland Grain Free with Real Meat + Sweet Potato Dry Dog Food',
 'product_name_Garland Food with Real Meat',
 'product_name_Garland Dog Food Health Weight Recipe',
 'product_name_Garland Classic Healthy Grains Dry Dog Food with Real Meat',
 'product_name_Flora Kibble Dry Dog Food, 20 lb, with Plant Based Protein',
 'product_name_Choice dult Dry Dog Food, Chicken & Steak',
 'product_name_Choice Small Dog Complete Nutrition Small Breed Adult Dry Dog Food Grilled Steak and Vegetable Flavor Dog',
 'product_name_Choice Small Breed Adult Dry Dog Food, Chicken & Steak',
 'product_name_Choice Dry Dog Food',
 'product_name_Choice Cuts in Gravy Adult Wet Dog Food, 3.5 oz. Pouches',
 'product_name_Choice Chopped Ground Dinner Adult Wet Dog Food, 3.5 oz. Pouches',
 'product_name_Bones Human Grade Dehydrated Whole Grain Dog Food – Complete Meal or Dog Food Topper',
 'product_name_Bezt ection Formula Natural Adult Large Breed Dry Dog Food',
 'product_name_Bezt ection Formula Natural Adult Beef and Brown Rice Dry Dog Food',
 'product_name_Bezt Natural Small Breed Wet Dog Food Cups, in Hearty Gravy, 3.5-oz Cups',
 'product_name_Bezt Natural Senior Wet Dog Food, Chicken 12.5-oz can (Pack of 12)',
 'product_name_Bezt Natural Senior Dry Dog Food, Chicken and Brown Rice',
 'product_name_Bezt Natural Adult Wet Dog Food, 12.5-oz cans (Pack of 12)',
 'product_name_Bezt Natural Adult Small Breed Dry Dog Food',
 'product_name_Bezt Natural Adult Large Breed Dry Dog Food',
 'product_name_Bezt Natural Adult Healthy Weight Chicken and Brown Rice Dry Dog Food',
 'product_name_Bezt Natural Adult Fish and Brown Rice Dry Dog Food',
 'product_name_Bezt Natural Adult Dry Dog Food',
 'product_name_Bezt Natural Adult Beef and Brown Rice Dry Dog Food',
 'product_name_Bezt High Protein, Natural Adult Dry Dog Food',
 'product_name_Bezt Adult Chicken and Brown Rice Recipe Dry Dog Food',
 'product_name_Beethoven e-Flavored Salmon High Protein Recipes Premium Dry Dog Food with Real Salmon, Superfoods and Nutrie',
 'product_name_Beethoven Wild Smoke-Flavored Salmon High Protein Recipes Premium Dry Dog Food with Real Salmon, Superfoods',
 'product_name_Beethoven Roasted Bison and Venison High Protein Real Meat Recipes Premium Dry Dog Food with Superfoods and N',
 'product_name_Beam y Dog Food, Beef, Pea & Brown Rice Recipe',
 'product_name_Beam st 6 Limited Ingredient Diet Dry Dog Food',
 'product_name_Beam sh Super Premium Dry Dog Food with Real Meat, Veggies & Fruit',
 'product_name_Beam emium Natural Dry Dog Food, Real Chicken & Veggies Recipe, 28 Pounds (Packaging May Vary)',
 'product_name_Beam Premium Natural Dry Dog Food, Real Chicken & Veggies Recipe, 28 Pounds',
 'product_name_Beam Just 6 Limited Ingredient Diet Dry Dog Food',
 'product_name_Beam Dry Dog Food, Beef, Pea & Brown Rice Recipe',
 'product_name_Beam Dish Super Premium Dry Dog Food with Real Meat, Veggies & Fruit',
 'product_name_Astro th Small Breed Dry Dog Food with Grains, Natural Ingredients, Made in USA with Real Turkey, for Dog',
 'product_name_Astro ee High-Protein Dry Dog Food, Natural Ingredients, Made in USA with Real Meat, All Breeds, for Adul',
 'product_name_Astro Small Breed Dry Dog Food with Grains, Natural Ingredients, Made in USA with Real Turkey, for Dogs U',
 'product_name_Astro Grain-Free High-Protein Dry Dog Food, Natural Ingredients, Made in USA with Real Meat, All Breeds,',
 'product_name_Arf lesome Grains Senior Dry Dog Food - Chicken & Brown Rice Recipe',
 'product_name_Arf Wholesome Grains Senior Dry Dog Food - Chicken & Brown Rice Recipe',
 'product_name_Arf Wholesome Grains Dry Dog Food (Chicken/Salmon/Beef/Lamb and Brown Rice)',
 'product_name_Arf Wholesome Grains Adult Healthy Weight Dry Dog Food - Chicken & Brown Rice Recipe',
 'product_name_Arf Wet Canned Dog Food 12.5/13.2 oz',
 'product_name_Arf Soft & Tender American Jerky Dog Treats',
 'product_name_Arf Jerky Dog Treats, 2 Lb Bag (Chicken, Duck, Sweet Potato Wraps)',
 'product_name_Arf Dry Dog Food Large Breed with Grains (Chicken and Brown Rice)',
 'product_name_Arf Dog Food, 35% Protein, No Added Grains (Beef, Salmon, Turkey, Lamb, Chicken)',
 'product_name_Alpha robiotics Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice',
 'product_name_Alpha n, Natural Dry Dog Food, True Instinct With Real Turkey & Venison - 7.4 lb. Bag',
 'product_name_Alpha ive Skin & Stomach, High Protein Dry Dog Food',
 'product_name_Alpha Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice (Packaging May Vary)',
 'product_name_Alpha Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice (Packagin',
 'product_name_Alpha Sensitive Skin & Stomach, High Protein Dry Dog Food',
 'product_name_Alpha Sensitive Skin & Stomach with Oats Adult Dry Dog Food',
 'product_name_Alpha Probiotics Shredded Blend High Protein, Adult Dry Dog Food Chicken & Rice',
 'product_name_Alpha Performance - High Protein Dry Dog Food - Chicken & Rice',
 'product_name_Alpha Natural Sensitive Systems, Skin & Coat Salmon Adult Dry Dog Food',
 'product_name_Alpha Natural Large Breed Formula Adult Dry Dog Food',
 'product_name_Alpha Natural Healthy Weight Formula Adult Dry Dog Food & Wet Dog Food',
 'product_name_Alpha Natural Dry Dog Food, True Instinct With Real Turkey & Venison - 7.4 lb. Bag',
 'product_name_Alpha Natural Dry Dog Food, True Instinct With Real Turkey & Venison - 15 lb. Bag',
 'product_name_Alpha Natural Adult Lamb & Rice Dry Dog Food',
 'product_name_Alpha Natural Adult Chicken & Rice Dry Dog Food',
 'product_name_Alpha Natural Adult Beef & Rice Dry Dog Food',
 'product_name_Alpha Moist & Meaty Steak Flavor Adult Dry Dog Food',
 'product_name_Alpha High Protein Dog Food with Probiotics for Dogs, Shredded Blend Turkey & Rice Formula - 17 lb. Bag',
 'product_name_Alpha ',
 'product_brand_Top',
 'product_brand_Seattle Gourmet',
 'product_brand_Ruby',
 'product_brand_Romero',
 'product_brand_Rivera',
 'product_brand_Playtime',
 'product_brand_Perro',
 'product_brand_Paws',
 'product_brand_Omaha',
 'product_brand_King',
 'product_brand_Kastle',
 'product_brand_K99',
 'product_brand_Hearth',
 'product_brand_Health One',
 'product_brand_Hanover',
 'product_brand_Garland',
 'product_brand_Flora',
 'product_brand_Choice',
 'product_brand_Bones',
 'product_brand_Bezt',
 'product_brand_Beethoven',
 'product_brand_Beam',
 'product_brand_Astro',
 'product_brand_Arf',
 'product_brand_Alpha',
 'ad_exp_Video ad',
 'ad_exp_Sponsored Products',
 'ad_exp_Sponsored Brands',
 'ad_exp_Some other type of ad',
 "ad_exp_Don't recall seeing an ad",
 'ad_exp_Display/banner ad',
 'sale_date_2022-09-30',
 'sale_date_2022-09-29',
 'sale_date_2022-09-28',
 'sale_date_2022-09-27',
 'sale_date_2022-09-26',
 'sale_date_2022-09-25',
 'sale_date_2022-09-24',
 'sale_date_2022-09-23',
 'sale_date_2022-09-22',
 'sale_date_2022-09-21',
 'sale_date_2022-09-20',
 'sale_date_2022-09-19',
 'sale_date_2022-09-18',
 'sale_date_2022-09-17',
 'sale_date_2022-09-16',
 'sale_date_2022-09-15',
 'sale_date_2022-09-14',
 'sale_date_2022-09-13',
 'sale_date_2022-09-12',
 'sale_date_2022-09-11',
 'sale_date_2022-09-10',
 'sale_date_2022-09-09',
 'sale_date_2022-09-08',
 'sale_date_2022-09-07',
 'sale_date_2022-09-06',
 'sale_date_2022-09-05',
 'sale_date_2022-09-04',
 'sale_date_2022-09-03',
 'sale_date_2022-09-02',
 'sale_date_2022-09-01',
 'sale_date_2022-08-31',
 'sale_date_2022-08-30',
 'sale_date_2022-08-29',
 'sale_date_2022-08-28',
 'sale_date_2022-08-27',
 'sale_date_2022-08-26',
 'sale_date_2022-08-25',
 'sale_date_2022-08-24',
 'sale_date_2022-08-23',
 'sale_date_2022-08-22',
 'sale_date_2022-08-21',
 'sale_date_2022-08-20',
 'sale_date_2022-08-19',
 'sale_date_2022-08-18',
 'sale_date_2022-08-17',
 'sale_date_2022-08-16',
 'sale_date_2022-08-15',
 'sale_date_2022-08-14',
 'sale_date_2022-08-13',
 'sale_date_2022-08-12',
 'sale_date_2022-08-11',
 'sale_date_2022-08-10',
 'sale_date_2022-08-09',
 'sale_date_2022-08-08',
 'sale_date_2022-08-07',
 'sale_date_2022-08-06',
 'sale_date_2022-08-05',
 'sale_date_2022-08-04',
 'sale_date_2022-08-03',
 'sale_date_2022-08-02',
 'sale_date_2022-08-01',
 'sale_date_2022-07-31',
 'sale_date_2022-07-30',
 'sale_date_2022-07-29',
 'sale_date_2022-07-28',
 'sale_date_2022-07-27',
 'sale_date_2022-07-26',
 'sale_date_2022-07-25',
 'sale_date_2022-07-24',
 'sale_date_2022-07-23',
 'sale_date_2022-07-22',
 'sale_date_2022-07-21',
 'sale_date_2022-07-20',
 'sale_date_2022-07-19',
 'sale_date_2022-07-18',
 'sale_date_2022-07-17',
 'sale_date_2022-07-16',
 'sale_date_2022-07-15',
 'sale_date_2022-07-14',
 'sale_date_2022-07-13',
 'sale_date_2022-07-12',
 'sale_date_2022-07-11',
 'sale_date_2022-07-10',
 'sale_date_2022-07-09',
 'sale_date_2022-07-08',
 'sale_date_2022-07-07',
 'sale_date_2022-07-06',
 'sale_date_2022-07-05',
 'sale_date_2022-07-04',
 'sale_date_2022-07-03',
 'sale_date_2022-07-02',
 'sale_date_2022-07-01',
 'sale_date_2022-06-30',
 'sale_date_2022-06-29',
 'sale_date_2022-06-28',
 'sale_date_2022-06-27',
 'sale_date_2022-06-26',
 'sale_date_2022-06-25',
 'sale_date_2022-06-24',
 'sale_date_2022-06-23',
 'sale_date_2022-06-22',
 'sale_date_2022-06-21',
 'sale_date_2022-06-20',
 'sale_date_2022-06-19',
 'sale_date_2022-06-18',
 'sale_date_2022-06-17',
 'sale_date_2022-06-16',
 'sale_date_2022-06-15',
 'sale_date_2022-06-14',
 'sale_date_2022-06-13',
 'sale_date_2022-06-12',
 'sale_date_2022-06-11',
 'sale_date_2022-06-10',
 'sale_date_2022-06-09',
 'sale_date_2022-06-08',
 'sale_date_2022-06-07',
 'sale_date_2022-06-06',
 'sale_date_2022-06-05',
 'sale_date_2022-06-04',
 'sale_date_2022-06-03',
 'sale_date_2022-06-02',
 'sale_date_2022-06-01',
 'sale_date_2022-05-31',
 'sale_date_2022-05-30',
 'sale_date_2022-05-29',
 'sale_date_2022-05-28',
 'sale_date_2022-05-27',
 'sale_date_2022-05-26',
 'sale_date_2022-05-25',
 'sale_date_2022-05-24',
 'sale_date_2022-05-23',
 'sale_date_2022-05-22',
 'sale_date_2022-05-21',
 'sale_date_2022-05-20',
 'sale_date_2022-05-19',
 'sale_date_2022-05-18',
 'sale_date_2022-05-17',
 'sale_date_2022-05-16',
 'sale_date_2022-05-15',
 'sale_date_2022-05-14',
 'sale_date_2022-05-13',
 'sale_date_2022-05-12',
 'sale_date_2022-05-11',
 'sale_date_2022-05-10',
 'sale_date_2022-05-09',
 'sale_date_2022-05-08',
 'sale_date_2022-05-07',
 'sale_date_2022-05-06',
 'sale_date_2022-05-05',
 'sale_date_2022-05-04',
 'sale_date_2022-05-03',
 'sale_date_2022-05-02',
 'sale_date_2022-05-01',
 'sale_date_2022-04-30',
 'sale_date_2022-04-29',
 'sale_date_2022-04-28',
 'sale_date_2022-04-27',
 'sale_date_2022-04-26',
 'sale_date_2022-04-25',
 'sale_date_2022-04-24',
 'sale_date_2022-04-23',
 'sale_date_2022-04-22',
 'sale_date_2022-04-21',
 'sale_date_2022-04-20',
 'sale_date_2022-04-19',
 'sale_date_2022-04-18',
 'sale_date_2022-04-17',
 'sale_date_2022-04-16',
 'sale_date_2022-04-15',
 'sale_date_2022-04-14',
 'sale_date_2022-04-13',
 'sale_date_2022-04-12',
 'sale_date_2022-04-11',
 'sale_date_2022-04-10',
 'sale_date_2022-04-09',
 'sale_date_2022-04-08',
 'sale_date_2022-04-07',
 'sale_date_2022-04-06',
 'sale_date_2022-04-05',
 'sale_date_2022-04-04',
 'sale_date_2022-04-03',
 'sale_date_2022-04-02',
 'sale_date_2022-04-01',
 'sale_date_2022-03-31',
 'sale_date_2022-03-30',
 'sale_date_2022-03-29',
 'sale_date_2022-03-28',
 'sale_date_2022-03-27',
 'sale_date_2022-03-26',
 'sale_date_2022-03-25',
 'sale_date_2022-03-24',
 'sale_date_2022-03-23',
 'sale_date_2022-03-22',
 'sale_date_2022-03-21',
 'sale_date_2022-03-20',
 'sale_date_2022-03-19',
 'sale_date_2022-03-18',
 'sale_date_2022-03-17',
 'sale_date_2022-03-16',
 'sale_date_2022-03-15',
 'sale_date_2022-03-14',
 'sale_date_2022-03-13',
 'sale_date_2022-03-12',
 'sale_date_2022-03-11',
 'sale_date_2022-03-10',
 'sale_date_2022-03-09',
 'sale_date_2022-03-08',
 'sale_date_2022-03-07',
 'sale_date_2022-03-06',
 'sale_date_2022-03-05',
 'sale_date_2022-03-04',
 'sale_date_2022-03-03',
 'sale_date_2022-03-02',
 'sale_date_2022-03-01',
 'sale_date_2022-02-28',
 'sale_date_2022-02-27',
 'sale_date_2022-02-26',
 'sale_date_2022-02-25',
 'sale_date_2022-02-24',
 'sale_date_2022-02-23',
 'sale_date_2022-02-22',
 'sale_date_2022-02-21',
 'sale_date_2022-02-20',
 'sale_date_2022-02-19',
 'sale_date_2022-02-18',
 'sale_date_2022-02-17',
 'sale_date_2022-02-16',
 'sale_date_2022-02-15',
 'sale_date_2022-02-14',
 'sale_date_2022-02-13',
 'sale_date_2022-02-12',
 'sale_date_2022-02-11',
 'sale_date_2022-02-10',
 'sale_date_2022-02-09',
 'sale_date_2022-02-08',
 'sale_date_2022-02-07',
 'sale_date_2022-02-06',
 'sale_date_2022-02-05',
 'sale_date_2022-02-04',
 'sale_date_2022-02-03',
 'sale_date_2022-02-02',
 'sale_date_2022-02-01',
 'sale_date_2022-01-31',
 'sale_date_2022-01-30',
 'sale_date_2022-01-29',
 'sale_date_2022-01-28',
 'sale_date_2022-01-27',
 'sale_date_2022-01-26',
 'sale_date_2022-01-25',
 'sale_date_2022-01-24',
 'sale_date_2022-01-23',
 'sale_date_2022-01-22',
 'sale_date_2022-01-21',
 'sale_date_2022-01-20',
 'sale_date_2022-01-19',
 'sale_date_2022-01-18',
 'sale_date_2022-01-17',
 'sale_date_2022-01-16',
 'sale_date_2022-01-15',
 'sale_date_2022-01-14',
 'sale_date_2022-01-13',
 'sale_date_2022-01-12',
 'sale_date_2022-01-11',
 'sale_date_2022-01-10',
 'sale_date_2022-01-09',
 'sale_date_2022-01-08',
 'sale_date_2022-01-07',
 'sale_date_2022-01-06',
 'sale_date_2022-01-05',
 'sale_date_2022-01-04',
 'sale_date_2022-01-03',
 'sale_date_2022-01-02',
 'sale_date_2022-01-01',
 'sale_date_2021-12-31',
 'sale_date_2021-12-30',
 'sale_date_2021-12-29',
 'sale_date_2021-12-28',
 'sale_date_2021-12-27',
 'sale_date_2021-12-26',
 'sale_date_2021-12-25',
 'sale_date_2021-12-24',
 'sale_date_2021-12-23',
 'sale_date_2021-12-22',
 'sale_date_2021-12-21',
 'sale_date_2021-12-20',
 'sale_date_2021-12-19',
 'sale_date_2021-12-18',
 'sale_date_2021-12-17',
 'sale_date_2021-12-16',
 'sale_date_2021-12-15',
 'sale_date_2021-12-14',
 'sale_date_2021-12-13',
 'sale_date_2021-12-12',
 'sale_date_2021-12-11',
 'sale_date_2021-12-10',
 'sale_date_2021-12-09',
 'sale_date_2021-12-08',
 'sale_date_2021-12-07',
 'sale_date_2021-12-06',
 'sale_date_2021-12-05',
 'sale_date_2021-12-04',
 'sale_date_2021-12-03',
 'sale_date_2021-12-02',
 'sale_date_2021-12-01',
 'sale_date_2021-11-30',
 'sale_date_2021-11-29',
 'sale_date_2021-11-28',
 'sale_date_2021-11-27',
 'sale_date_2021-11-26',
 'sale_date_2021-11-25',
 'sale_date_2021-11-24',
 'sale_date_2021-11-23',
 'sale_date_2021-11-22',
 'sale_date_2021-11-21',
 'sale_date_2021-11-20',
 'sale_date_2021-11-19',
 'sale_date_2021-11-18',
 'sale_date_2021-11-17',
 'sale_date_2021-11-16',
 'sale_date_2021-11-15',
 'sale_date_2021-11-14',
 'sale_date_2021-11-13',
 'sale_date_2021-11-12',
 'sale_date_2021-11-11',
 'sale_date_2021-11-10',
 'sale_date_2021-11-09',
 'sale_date_2021-11-08',
 'sale_date_2021-11-07',
 ...]


columns_ad_exp = ['ad_exp_Display/banner ad',
 "ad_exp_Don't recall seeing an ad",
 'ad_exp_Some other type of ad',
 'ad_exp_Sponsored Brands',
 'ad_exp_Sponsored Products',
 'ad_exp_Video ad']
max_column = ''
max_count = -1
for column in columns_ad_exp:
  count = df8[column].sum()
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = ad_exp_Don't recall seeing an ad,  count = 113


columns_brand = ['product_brand_Alpha',
 'product_brand_Arf',
 'product_brand_Astro',
 'product_brand_Beam',
 'product_brand_Beethoven',
 'product_brand_Bezt',
 'product_brand_Bones',
 'product_brand_Choice',
 'product_brand_Flora',
 'product_brand_Garland',
 'product_brand_Hanover',
 'product_brand_Health One',
 'product_brand_Hearth',
 'product_brand_K99',
 'product_brand_Kastle',
 'product_brand_King',
 'product_brand_Omaha',
 'product_brand_Paws',
 'product_brand_Perro',
 'product_brand_Playtime',
 'product_brand_Rivera',
 'product_brand_Romero',
 'product_brand_Ruby',
 'product_brand_Seattle Gourmet',
 'product_brand_Top']
max_column = ''
max_count = -1
for column in columns_brand:
  count = df8[column].sum()
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = product_brand_Alpha,  count = 122


columns_gender = [ 'gender_F',
 'gender_M']
max_column = ''
max_count = -1
for column in columns_gender:
  count = df8[column].sum()
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = gender_M,  count = 204


sum(df8['prime'])

295


columns_marital = [ 'marital_Single',
 'marital_Married',
 'marital_Domestic partner/serious relationship']
max_column = ''
max_count = -1
for column in columns_marital:
  count = df8[column].sum()
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = marital_Married,  count = 198


columns_education = [ 'education_Some college or trade school',
 'education_Post graduate',
 'education_High school graduate',
 'education_College graduate']
max_column = ''
max_count = -1
for column in columns_education:
  count = df8[column].sum()
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = education_College graduate,  count = 188


columns_income = ['income_Less than $20,000',
 'income_$80,000 - $99,999',
 'income_$60,000 - $79,999',
 'income_$40,000 - $59,999',
 'income_$20,000 - $39,999',
 'income_$100,000 or more']
max_column = ''
max_count = -1
for column in columns_income:
  count = df8[column].sum()
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = income_$100,000 or more,  count = 122


columns_age = ['age_65+',
 'age_55-64',
 'age_45-54',
 'age_35-44',
 'age_25-34',
 'age_18-24']
max_column = ''
max_count = -1
for column in columns_age:
  count = df8[column].sum()
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = age_45-54,  count = 92


df8.head()


df1.head()


from statistics import mean
mean(df0['price']*df0['qty'])

-0.015045486214909818


mean(df1['price']*df1['qty'])

-0.024412121773835907


mean(df2['price']*df2['qty'])

0.08744795926327455


mean(df3['price']*df3['qty'])

-0.024019945030047857


mean(df4['price']*df4['qty'])

-0.0200793420043912


mean(df5['price']*df5['qty'])

-0.052724937111071644


mean(df6['price']*df6['qty'])

0.06573791243837343


mean(df7['price']*df7['qty'])

-0.05638635074643973


mean(df8['price']*df8['qty'])

0.0837901853442486


mean(df9['price'])

-0.03373996008532421


d = {'cluster': ['df0', 'df1', 'df2', 'df3', 'df4', 'df5', 'df6', 'df7', 'df8', 'df9'], 
     'pricexquantity': [mean(df0['price']*df0['qty']), mean(df1['price']*df1['qty']), 
                        mean(df2['price']*df2['qty']),mean(df3['price']*df3['qty']),
                        mean(df4['price']*df4['qty']), mean(df5['price']*df5['qty']),
                        mean(df6['price']*df6['qty']), mean(df7['price']*df7['qty']), 
                        mean(df8['price']*df8['qty']), mean(df9['price']*df9['qty']), 
               ],
     'rows': [len(df0), len(df1), len(df2), len(df3), len(df4), len(df5), len(df6), 
              len(df7), len(df8), len(df9)]
}
result = pd.DataFrame(d)
result


from sklearn import preprocessing
x = np.array(result.iloc[:,1]) #returns a numpy array
min_max_scaler = preprocessing.MinMaxScaler()
x_scaled = min_max_scaler.fit_transform(x.reshape(10,1))
result['pq_normal'] = x_scaled

x = np.array(result.iloc[:,2]) #returns a numpy array
x_scaled = min_max_scaler.fit_transform(x.reshape(10,1))
result['rows_normal'] = x_scaled
print(result)

  cluster  pricexquantity  rows  pq_normal  rows_normal
0     df0       -0.015045   963   0.287420     0.530990
1     df1       -0.024412   685   0.222299     0.273821
2     df2        0.087448  1470   1.000000     1.000000
3     df3       -0.024020  1108   0.225026     0.665125
4     df4       -0.020079  1340   0.252422     0.879741
5     df5       -0.052725   862   0.025456     0.437558
6     df6        0.065738   810   0.849062     0.389454
7     df7       -0.056386   783   0.000000     0.364477
8     df8        0.083790   389   0.974570     0.000000
9     df9       -0.020267   484   0.251117     0.087882


def Woof(result_df, input_df, train_df):
  input_df = pd.DataFrame(input_df)
  df = pd.concat([train_df, input_df], axis = 0)
  labels = hierarchical_cluster.fit_predict(df)
  n = len(input_df)
  new_data_cluster = labels[n-1]
  return result_df.iloc[new_data_cluster][3]


Woof(result, test_df, df_Fel_onehot)

0.0


row1 = np.array(df_Fel_onehot.iloc[2,:])
test_df = pd.DataFrame(row1.reshape(-1, len(row1)))


test_df
test_df.columns = df_Fel_onehot.columns


df = pd.concat([df_Fel_onehot, test_df])
df


test_df.columns = df_Fel_onehot.columns
test_df


test_df

df8


columns_brand = ['product_brand_Alpha',
 'product_brand_Arf',
 'product_brand_Astro',
 'product_brand_Beam',
 'product_brand_Beethoven',
 'product_brand_Bezt',
 'product_brand_Bones',
 'product_brand_Choice',
 'product_brand_Flora',
 'product_brand_Garland',
 'product_brand_Hanover',
 'product_brand_Health One',
 'product_brand_Hearth',
 'product_brand_K99',
 'product_brand_Kastle',
 'product_brand_King',
 'product_brand_Omaha',
 'product_brand_Paws',
 'product_brand_Perro',
 'product_brand_Playtime',
 'product_brand_Rivera',
 'product_brand_Romero',
 'product_brand_Ruby',
 'product_brand_Seattle Gourmet',
 'product_brand_Top']
max_column = ''
max_count = -1
for column in columns_brand:
  count = df2[column].sum()/len(df2)
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))

max_column = product_brand_Alpha,  count = 0.32789115646258504


columns_brand = ['product_brand_Alpha',
 'product_brand_Arf',
 'product_brand_Astro',
 'product_brand_Beam',
 'product_brand_Beethoven',
 'product_brand_Bezt',
 'product_brand_Bones',
 'product_brand_Choice',
 'product_brand_Flora',
 'product_brand_Garland',
 'product_brand_Hanover',
 'product_brand_Health One',
 'product_brand_Hearth',
 'product_brand_K99',
 'product_brand_Kastle',
 'product_brand_King',
 'product_brand_Omaha',
 'product_brand_Paws',
 'product_brand_Perro',
 'product_brand_Playtime',
 'product_brand_Rivera',
 'product_brand_Romero',
 'product_brand_Ruby',
 'product_brand_Seattle Gourmet',
 'product_brand_Top']
max_column = ''
max_count = -1
worst = []
for column in columns_brand:
  count = df7[column].sum()/len(df7)
  worst.append(count)
  if count > max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))
worst

max_column = product_brand_Alpha,  count = 0.30140485312899107

[0.30140485312899107,
 0.12643678160919541,
 0.01277139208173691,
 0.020434227330779056,
 0.006385696040868455,
 0.1724137931034483,
 0.0038314176245210726,
 0.04469987228607918,
 0.005108556832694764,
 0.03065134099616858,
 0.007662835249042145,
 0.08045977011494253,
 0.005108556832694764,
 0.006385696040868455,
 0.006385696040868455,
 0.024265644955300127,
 0.005108556832694764,
 0.01532567049808429,
 0.011494252873563218,
 0.001277139208173691,
 0.006385696040868455,
 0.008939974457215836,
 0.019157088122605363,
 0.04469987228607918,
 0.033205619412515965]


columns_brand = ['product_brand_Alpha',
 'product_brand_Arf',
 'product_brand_Astro',
 'product_brand_Beam',
 'product_brand_Beethoven',
 'product_brand_Bezt',
 'product_brand_Bones',
 'product_brand_Choice',
 'product_brand_Flora',
 'product_brand_Garland',
 'product_brand_Hanover',
 'product_brand_Health One',
 'product_brand_Hearth',
 'product_brand_K99',
 'product_brand_Kastle',
 'product_brand_King',
 'product_brand_Omaha',
 'product_brand_Paws',
 'product_brand_Perro',
 'product_brand_Playtime',
 'product_brand_Rivera',
 'product_brand_Romero',
 'product_brand_Ruby',
 'product_brand_Seattle Gourmet',
 'product_brand_Top']
max_column = ''
max_count = 1
best = []
for column in columns_brand:
  count = df2[column].sum()/len(df2)
  best.append(count)
  if count < max_count:
    max_count = count
    max_column = column
print('max_column = {},  count = {}'.format(max_column, max_count))
worst

max_column = product_brand_Kastle,  count = 0.004761904761904762

[0.30140485312899107,
 0.12643678160919541,
 0.01277139208173691,
 0.020434227330779056,
 0.006385696040868455,
 0.1724137931034483,
 0.0038314176245210726,
 0.04469987228607918,
 0.005108556832694764,
 0.03065134099616858,
 0.007662835249042145,
 0.08045977011494253,
 0.005108556832694764,
 0.006385696040868455,
 0.006385696040868455,
 0.024265644955300127,
 0.005108556832694764,
 0.01532567049808429,
 0.011494252873563218,
 0.001277139208173691,
 0.006385696040868455,
 0.008939974457215836,
 0.019157088122605363,
 0.04469987228607918,
 0.033205619412515965]

	sale_date	ad_exp	sns	product_brand	product_name	price	qty	gender	city	st	zip	lat	lng	marital	education	income	age	prime
0	2021-10-01	Don't recall seeing an ad	0	Alpha	Alpha Natural Sensitive Systems, Skin & Coat S...	0.490374	1	F	Boise	ID	83711	43.4599	-116.2440	Married	Some college or trade school	$80,000 - $99,999	55-64	0
1	2021-10-01	Don't recall seeing an ad	1	Arf	Arf Soft & Tender American Jerky Dog Treats	-1.380585	1	F	Durham	NC	27710	36.0512	-78.8577	Married	High school graduate	$100,000 or more	45-54	1
2	2021-10-01	Don't recall seeing an ad	0	Bezt	Bezt Adult Chicken and Brown Rice Recipe Dry D...	-1.245769	1	M	Phoenix	AZ	85099	33.2765	-112.1872	Married	College graduate	$100,000 or more	45-54	1
3	2021-10-01	Don't recall seeing an ad	0	Alpha	Alpha Probiotics Shredded Blend High Protein, ...	2.004318	1	F	Portsmouth	NH	214	43.0059	-71.0132	Married	Some college or trade school	$100,000 or more	55-64	1
4	2021-10-01	Don't recall seeing an ad	0	Alpha	Alpha Natural Adult Lamb & Rice Dry Dog Food	-0.699510	1	F	Chicago	IL	60624	41.8804	-87.7223	Single	Some college or trade school	$40,000 - $59,999	25-34	1

	sns	price	qty	zip	lat	lng	prime	sale_date_2021-10-01	sale_date_2021-10-02	sale_date_2021-10-03	...	income_$40,000 - $59,999	income_$60,000 - $79,999	income_$80,000 - $99,999	income_Less than $20,000	age_18-24	age_25-34	age_35-44	age_45-54	age_55-64	age_65+
19	0	-1.350127	1	70116	29.9686	-90.0646	1	0	1	0	...	0	0	0	0	0	0	1	0	0	0
29	0	-0.770414	1	68517	40.9317	-96.6045	1	0	0	1	...	0	0	0	0	0	0	0	0	1	0
30	0	-1.007592	1	66160	39.0966	-94.7495	1	0	0	1	...	0	0	1	0	0	0	0	0	1	0
41	0	3.381947	1	70179	30.0330	-89.8826	1	0	0	0	...	0	0	1	0	0	0	0	0	1	0
71	0	0.260186	1	70165	30.0330	-89.8826	1	0	0	0	...	0	1	0	0	0	0	1	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
8798	0	-0.559700	1	66225	38.8999	-94.8320	0	0	0	0	...	1	0	0	0	0	0	0	1	0	0
8799	0	-0.691022	2	71151	32.6076	-93.7526	1	0	0	0	...	0	0	0	0	0	0	1	0	0	0
8860	0	0.939763	1	68197	41.2490	-96.0274	0	0	0	0	...	0	0	0	0	0	0	1	0	0	0
8864	0	-1.008091	1	68164	41.2955	-96.1008	1	0	0	0	...	0	1	0	0	0	0	0	0	1	0
8879	0	0.097407	1	66105	39.0850	-94.6356	1	0	0	0	...	1	0	0	0	0	0	0	0	1	0

	cluster	pricexquantity	rows
0	df0	-0.015045	963
1	df1	-0.024412	685
2	df2	0.087448	1470
3	df3	-0.024020	1108
4	df4	-0.020079	1340
5	df5	-0.052725	862
6	df6	0.065738	810
7	df7	-0.056386	783
8	df8	0.083790	389
9	df9	-0.020267	484

	sns	price	qty	zip	lat	lng	prime	sale_date_2021-10-01	sale_date_2021-10-02	sale_date_2021-10-03	...	income_$40,000 - $59,999	income_$60,000 - $79,999	income_$80,000 - $99,999	income_Less than $20,000	age_18-24	age_25-34	age_35-44	age_45-54	age_55-64	age_65+
0	0.0	0.490374	1.0	83711.0	43.4599	-116.2440	0.0	1.0	0.0	0.0	...	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
1	1.0	-1.380585	1.0	27710.0	36.0512	-78.8577	1.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
2	0.0	-1.245769	1.0	85099.0	33.2765	-112.1872	1.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
3	0.0	2.004318	1.0	214.0	43.0059	-71.0132	1.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
4	0.0	-0.699510	1.0	60624.0	41.8804	-87.7223	1.0	1.0	0.0	0.0	...	1.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
8890	0.0	0.747524	1.0	47306.0	40.2023	-85.4082	1.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0
8891	0.0	-1.150398	2.0	75251.0	32.9189	-96.7751	1.0	0.0	0.0	0.0	...	0.0	0.0	0.0	1.0	0.0	1.0	0.0	0.0	0.0	0.0
8892	0.0	1.738678	1.0	6140.0	41.7918	-72.7188	1.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
8893	0.0	0.205261	1.0	8104.0	39.9186	-75.1078	1.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
0	0.0	-1.245769	1.0	85099.0	33.2765	-112.1872	1.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0