apriori algorithm python update

-
from mlxtend.frequent_patterns import apriori, association_rules
from mlxtend.preprocessing import TransactionEncoder
import pandas as pd

dataset = [
    ['I1', 'I2', 'I3', 'I4'],
    ['I1', 'I2', 'I3'],
    ['I1', 'I2'],
    ['I1', 'I4'],
    ['I2', 'I4']
]

te = TransactionEncoder()
te_ary = te.fit(dataset).transform(dataset)
df = pd.DataFrame(te_ary, columns=te.columns_)

print("Transaction Data:")
print(df)

frequent_itemsets = apriori(df, min_support=0.4, use_colnames=True)
print("\nFrequent Itemsets:")
print(frequent_itemsets)

rules = association_rules(frequent_itemsets, metric="confidence", min_threshold=0.6)
print("\nAssociation Rules:")
print(rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']])

Output 

Transaction Data:
      I1 I2 I3 I4
0 True True True True
1 True True True False
2 True True False False
3 True False False True
4 False True False True

Frequent Itemsets:
   support itemsets
0 0.8 (I1)
1 0.8 (I2)
2 0.4 (I3)
3 0.6 (I4)
4 0.6 (I1, I2)
5 0.4 (I1, I3)
6 0.4 (I1, I4)
7 0.4 (I2, I3)
8 0.4 (I2, I4)

Association Rules:
  antecedents consequents support confidence lift
0 (I1) (I2) 0.6 0.750000 0.937500
1 (I2) (I1) 0.6 0.750000 0.937500
2 (I4) (I1) 0.4 0.666667 0.833333
3 (I4) (I2) 0.4 0.666667 0.833333
4 (I3) (I1) 0.4 1.000000 1.250000
5 (I3) (I2) 0.4 1.000000 1.250000

Comments

Post a Comment

Popular posts from this blog

Dijkstra's Algorithm Matrix

-
  #include <stdio.h> #include <stdlib.h> #include <limits.h> #define MAX 100 #define INF INT_MAX int adj[MAX][MAX]; int dist[MAX]; int pred[MAX]; int visited[MAX]; void create_graph(int n, int gtype); void dijkstra(int n, int source); void print_shortest_path(int source, int destination); int main() {     int n, gtype, source;     printf("Enter 1 for undirected graph and -1 for directed graph: ");     scanf("%d", &gtype);     printf("Enter the number of vertices: ");     scanf("%d", &n);     create_graph(n, gtype);     printf("Enter the source vertex: ");     scanf("%d", &source);     dijkstra(n, source);     for (int i = 0; i < n; i++) {         if (i != source) {             printf("Shortest path from vertex %d to vertex %d: ", source, i);             print_shortest_path...
Read more

k means JDK java

-
import java.util.*; public class KMeansDynamic {     public static void main(String[] args) {         Scanner sc = new Scanner(System.in);         System.out.print("Enter number of data points: ");         int n = sc.nextInt();         System.out.print("Enter number of features: ");         int f = sc.nextInt();         double[][] data = new double[n][f];         for (int i = 0; i < n; i++) {             System.out.print("Enter features for data point " + (i + 1) + " separated by space: ");             for (int j = 0; j < f; j++) {                 data[i][j] = sc.nextDouble();             }         }         System.out.print("Enter number of clusters (k): ");   ...
Read more

Chi square test

-
import numpy as np from scipy.stats import chi2_contingency r=int(input("Enter number of rows: ")) c=int(input("Enter number of columns: ")) observed=[] print("Enter observed values:") for i in range(r):     row=list(map(float,input(). split()))     observed.append(row) observed=np.array(observed) chi2,p,dof,expected=chi2_ contingency(observed) print("\nChi-Square Value:",chi2) print("Degrees of Freedom:",dof) print("Expected Frequencies:\n",expected) print("P-Value:",p) alpha=0.05 if p<alpha:     print("\nConclusion: Reject the Null Hypothesis (Variables are dependent)") else:     print("\nConclusion: Fail to Reject the Null Hypothesis (Variables are independent)") Output: Enter number of rows: 2 Enter number of columns: 2 Enter observed values: 50 30 20 40 Chi-Square Value: 10.529166666666667 Degrees of Freedom: 1 Expected Frequencies:  [[40. 40.]  [30. 30.]] P-Value: 0.0011750518530845063 Co...
Read more