renaming

5/data science/r/5.rmd

@@ -0,0 +1,103 @@
+---
+title: "Lab5: Associative rules, Apriori"
+author: "Vladislav Litvinov <vlad@sek1ro>"
+output:
+  pdf_document:
+  toc_float: TRUE
+---
+# Histogram of transaction frequencies
+```{r}
+setwd('/home/sek1ro/git/public/lab/ds/25-1/r')
+library(arules)
+library(arulesViz)
+ts = read.transactions("AssociationRules.csv",
+                       sep = " ",
+                       rm.duplicates = TRUE)
+
+itemFrequencyPlot(ts, type = "absolute", topN = 10)
+ift = sort(itemFrequency(ts), decreasing = TRUE)
+
+(most_frequent_item = ift[1])
+(max_ts_size = max(size(ts)))
+```
+# Model training. Rules computing
+```{r}
+rules = apriori(ts, parameter = list(support = 0.01, confidence = 0))
+length(rules)
+plot(rules, jitter = 0)
+
+rules50 = apriori(ts, parameter = list(support = 0.01, confidence = 0.5))
+length(rules50)
+plot(rules50, jitter = 0)
+```
+# Manual threshold applying: confidence = 0.5, plots comparsion
+```{r}
+library(ggplot2)
+asc = function(q, colors = c("lightgray", "red")) {
+  q = q[order(q$lift), ]
+  ggplot(q, aes(x = support, y = confidence, color = lift)) +
+    geom_point() +
+    ylim(0, 1) +
+    xlim(0, 0.5) +
+    theme_minimal() +
+      scale_color_gradientn(
+      colors = colors,
+      name = "Lift",
+      limits = c(min(q$lift), max(q$lift))
+    )
+}
+
+quality50 = as.data.frame(quality(rules50))
+asc(quality50, colors = c("navy", "cyan"))
+
+quality = as.data.frame(quality(rules))
+asc(subset(quality, quality$confidence > 0.5))
+```
+# Top 3 rules by lift. 'Relation' graph and matrix
+```{r}
+plot(rules, measure = c("support", "lift"), shading = "confidence")
+plot(rules)
+
+filt_rules = rules[which(quality(rules)$confidence > 0.8)]
+quality = as.data.frame(quality(filt_rules))
+quality = quality[order(-quality$lift),]
+tail(quality, 10)
+
+plot(filt_rules,
+     method = "matrix",
+     shading = c("lift", "confidence"),
+     engine = "grid")
+
+top3_rules = head(sort(filt_rules, by = "lift", decreasing = TRUE), 3)
+plot(top3_rules, method = "graph")
+```
+# Random picking of train and test datasets
+```{r}
+train_set = ts[1:8000]
+test_set = ts[8001:10000]
+
+train_rules = apriori(train_set, parameter = list(support = 0.01, confidence = 0.5))
+test_quality = interestMeasure(train_rules, 
+                                measure = c("support", "confidence", "lift", "coverage"),
+                                transactions = test_set)
+comparison <- data.frame(
+  train_support = quality(train_rules)$support[1:10],
+  test_support = test_quality$support[1:10],
+  train_lift = quality(train_rules)$lift[1:10],
+  test_lift = test_quality$lift[1:10]
+)
+
+print(comparison)
+plot(comparison$train_lift, comparison$test_lift,
+     xlab = "train lift", 
+     ylab = "test lift",
+     pch = 19)
+abline(0, 1, lty = 2)
+
+# График для support
+plot(comparison$train_support, comparison$test_support,
+     xlab = "train support", 
+     ylab = "test support",
+     pch = 19)
+abline(0, 1, lty = 2)
+```