| import pandas as pd |
| from itertools import combinations |
| from collections import defaultdict |
| import json |
| import os |
|
|
| class AprioriModel: |
| def __init__(self, min_support=0.01): |
| self.min_support = min_support |
| self.transactions = [] |
|
|
| def load_data(self, folder_path): |
| """Load CSV files from a folder and combine them into a single DataFrame.""" |
| combined_df = pd.DataFrame() |
| |
| for file in os.listdir(folder_path): |
| if file.endswith('.csv'): |
| file_path = os.path.join(folder_path, file) |
| df = pd.read_csv(file_path) |
| combined_df = pd.concat([combined_df, df], ignore_index=True) |
| |
| return combined_df |
|
|
| def preprocess_data(self, data): |
| """Prepare basket data and transaction sets from raw data.""" |
| basket = data.groupby(['Transaction ID', 'Product'])['Quantity'].sum().unstack().fillna(0) |
| basket = basket.applymap(lambda x: 1 if x > 0 else 0) |
|
|
| for _, row in basket.iterrows(): |
| self.transactions.append(set(row[row == 1].index)) |
|
|
| return basket |
|
|
| def calculate_pair_support(self): |
| """Calculate support for all pairs in the transactions.""" |
| pair_count = defaultdict(int) |
| |
| for transaction in self.transactions: |
| for pair in combinations(transaction, 2): |
| pair_count[frozenset(pair)] += 1 |
| |
| return { |
| pair: count for pair, count in pair_count.items() |
| if count / len(self.transactions) >= self.min_support |
| } |
|
|
| def generate_rules(self, frequent_pairs): |
| """Generate association rules based on frequent pairs.""" |
| rules = [] |
|
|
| for pair, support_count in frequent_pairs.items(): |
| for item in pair: |
| antecedent = frozenset([item]) |
| consequent = pair - antecedent |
|
|
| antecedent_support = sum(1 for t in self.transactions if antecedent.issubset(t)) / len(self.transactions) |
| confidence = (support_count / len(self.transactions)) / antecedent_support |
| consequent_support = sum(1 for t in self.transactions if consequent.issubset(t)) / len(self.transactions) |
| lift = confidence / consequent_support |
|
|
| rules.append({ |
| "Driver": list(antecedent)[0], |
| "Attach": list(consequent)[0], |
| "Support": support_count / len(self.transactions), |
| "Confidence": confidence, |
| "Lift": lift |
| }) |
|
|
| return rules |
|
|
| def save_rules(self, rules, output_path): |
| """Save generated rules to a CSV file.""" |
| rules_df = pd.DataFrame(rules) |
| rules_df.to_csv(output_path, index=False) |
| print("Rules saved successfully to", output_path) |
|
|
| |
| def predict(data): |
| |
| model = AprioriModel(min_support=0.01) |
| processed_data = model.load_data(data['folder_path']) |
| model.preprocess_data(processed_data) |
| frequent_pairs = model.calculate_pair_support() |
| rules = model.generate_rules(frequent_pairs) |
| return rules |
