[Python] DataFrames with non-bool types result in worse computationalperformance

This is the error am seeing in the image and the warning on my terminal

C:\Users\BALLER\Downloads\cs_model\venv\Lib\site-packages\mlxtend\frequent_patterns\fpcommon.py:109: DeprecationWarning:

DataFrames with non-bool types result in worse computationalperformance and their support might be discontinued in the future.Please use a DataFrame with bool type

My code #Merging Cluster with Main dataframe sel_Cluster = RFM_Table[['RESPID','Cluster']] Merged_DF_RFM_Table_Cluster= pd.merge(Merged_DF_RFM_Table,sel_Cluster,on='RESPID') #Merged_DF_RFM_Table_Cluster

cluster_Two=Merged_DF_RFM_Table_Cluster[Merged_DF_RFM_Table_Cluster.Cluster == 2]
cluster_One=Merged_DF_RFM_Table_Cluster[Merged_DF_RFM_Table_Cluster.Cluster == 1]
cluster_Zero=Merged_DF_RFM_Table_Cluster[Merged_DF_RFM_Table_Cluster.Cluster == 0]

#Finding frequency item set for Cluster 2
basket_Cluster_two = (cluster_Two.groupby(['RESPID','PRODUCE'])['QUANTITY']
.sum().unstack().reset_index().fillna(0)
.set_index('RESPID'))

def encode_units(x):
if x <= 0:
return 0
if x >= 1:
return 1

basket_cluster_two_sets = basket_Cluster_two.copy()
basket_cluster_two_sets = basket_cluster_two_sets.applymap(encode_units)

#Finding frequency item set for Cluster 1
basket_Cluster_one = (cluster_One.groupby(['RESPID','PRODUCE'])['QUANTITY']
.sum().unstack().reset_index().fillna(0)
.set_index('RESPID'))

def encode_units(x):
if x <= 0:
return 0
if x >= 1:
return 1

basket_cluster_one_sets = basket_Cluster_one.copy()
basket_cluster_one_sets = basket_cluster_one_sets.applymap(encode_units)

#Finding frequency item set for Cluster 0
basket_Cluster_zero = (cluster_Zero.groupby(['RESPID','PRODUCE'])['QUANTITY']
.sum().unstack().reset_index().fillna(0)
.set_index('RESPID'))

def encode_units(x):
if x <= 0:
return 0
if x >= 1:
return 1

basket_cluster_zero_sets = basket_Cluster_zero.copy()
basket_cluster_zero_sets = basket_cluster_zero_sets.applymap(encode_units)

from mlxtend.frequent_patterns import apriori
from mlxtend.frequent_patterns import association_rules



#%matplotlib inline
frequent_itemsets_cluster_two=apriori(basket_cluster_two_sets, min_support=0.03, use_colnames=True)
frequent_itemsets_cluster_one=apriori(basket_cluster_one_sets, min_support=0.02, use_colnames=True)
frequent_itemsets_cluster_zero=apriori(basket_cluster_zero_sets, min_support=0.01, use_colnames=True)
#fic_zero=apriori(basket_cluster_zero_sets, min_support=0.001, min_confidence=0.5, min_lift=3, min_length=1, use_colnames=True)

#Build frequent itemsets for Cluster two
frequent_itemsets_cluster_two['length'] = frequent_itemsets_cluster_two['itemsets'].apply(lambda x: len(x))
rules_cluster_two = association_rules(frequent_itemsets_cluster_two, metric="lift", min_threshold=1)


#Build frequent itemsets for Cluster one
frequent_itemsets_cluster_one['length'] = frequent_itemsets_cluster_one['itemsets'].apply(lambda x: len(x))
rules_cluster_one = association_rules(frequent_itemsets_cluster_one, metric="lift", min_threshold=1)


#Build frequent itemsets for Cluster Zero
frequent_itemsets_cluster_zero['length'] = frequent_itemsets_cluster_zero['itemsets'].apply(lambda x: len(x))
rules_cluster_zero = association_rules(frequent_itemsets_cluster_zero, metric="lift", min_threshold=1)

Continue reading...