1284 lines (1283 with data), 46.0 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cl2: 4 7 3 1 5 4 3 3 10 4 5 5 9 3 10 5 6 8 2 2 1 7 3 1 1 5 9 10 3 2 8 2 8 1 10 2 8 9 6 8 2 6 8 6 5 2 7 4 4 1 5 8 6 1 3 2 6 9 1 1 9 1 4 6 8 6 1 9 8 1 10 1 4 5 2 10 6 8 6 4 3 10 3 9 5 4 9 9 9 5 1 7 10 1 7 10 4 10 3 2 \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"IOPub data rate exceeded.\n",
"The notebook server will temporarily stop sending output\n",
"to the client in order to avoid crashing it.\n",
"To change this limit, set the config variable\n",
"`--NotebookApp.iopub_data_rate_limit`.\n",
"\n",
"Current values:\n",
"NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
"NotebookApp.rate_limit_window=3.0 (secs)\n",
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<caption>A matrix: 10 × 1 of type dbl</caption>\n",
"<tbody>\n",
"\t<tr><td>0.7515000</td></tr>\n",
"\t<tr><td>0.7611857</td></tr>\n",
"\t<tr><td>0.7651143</td></tr>\n",
"\t<tr><td>0.7584012</td></tr>\n",
"\t<tr><td>0.7577496</td></tr>\n",
"\t<tr><td>0.7632258</td></tr>\n",
"\t<tr><td>0.7605238</td></tr>\n",
"\t<tr><td>0.7674000</td></tr>\n",
"\t<tr><td>0.7581286</td></tr>\n",
"\t<tr><td>0.7734583</td></tr>\n",
"</tbody>\n",
"</table>\n"
],
"text/latex": [
"A matrix: 10 × 1 of type dbl\n",
"\\begin{tabular}{l}\n",
"\t 0.7515000\\\\\n",
"\t 0.7611857\\\\\n",
"\t 0.7651143\\\\\n",
"\t 0.7584012\\\\\n",
"\t 0.7577496\\\\\n",
"\t 0.7632258\\\\\n",
"\t 0.7605238\\\\\n",
"\t 0.7674000\\\\\n",
"\t 0.7581286\\\\\n",
"\t 0.7734583\\\\\n",
"\\end{tabular}\n"
],
"text/markdown": [
"\n",
"A matrix: 10 × 1 of type dbl\n",
"\n",
"| 0.7515000 |\n",
"| 0.7611857 |\n",
"| 0.7651143 |\n",
"| 0.7584012 |\n",
"| 0.7577496 |\n",
"| 0.7632258 |\n",
"| 0.7605238 |\n",
"| 0.7674000 |\n",
"| 0.7581286 |\n",
"| 0.7734583 |\n",
"\n"
],
"text/plain": [
" [,1] \n",
" [1,] 0.7515000\n",
" [2,] 0.7611857\n",
" [3,] 0.7651143\n",
" [4,] 0.7584012\n",
" [5,] 0.7577496\n",
" [6,] 0.7632258\n",
" [7,] 0.7605238\n",
" [8,] 0.7674000\n",
" [9,] 0.7581286\n",
"[10,] 0.7734583"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"number_cl=10\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/10/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/10/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:1000) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cl2: 4 7 3 1 5 4 3 3 10 4 5 5 9 3 10 5 6 8 2 2 1 7 3 1 1 5 9 10 3 2 8 2 8 1 10 2 8 9 6 8 2 6 8 6 5 2 7 4 4 1 5 8 6 1 3 2 6 9 1 1 9 1 4 6 8 6 1 9 8 1 10 1 4 5 2 10 6 8 6 4 3 10 3 9 5 4 9 9 9 5 1 7 10 1 7 10 4 10 3 2 \n"
]
}
],
"source": [
"number_cl=10\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/10/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/10/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:100) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"number_cl=10\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/10/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/10/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/10/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:100) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"number_cl=15\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/15/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:1000) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" #cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" #cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" #cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" #cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cl2: 7 7 12 2 5 15 7 10 15 8 13 4 3 7 15 10 2 2 9 14 2 13 10 10 13 8 1 9 10 11 12 15 9 2 12 14 6 11 3 1 5 8 6 2 13 11 5 4 8 7 5 1 1 12 14 15 3 9 5 10 1 13 11 6 5 3 4 6 6 8 3 9 11 6 14 14 7 13 6 4 9 15 13 11 12 11 2 5 3 9 15 14 4 1 1 7 8 12 4 3 \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"IOPub data rate exceeded.\n",
"The notebook server will temporarily stop sending output\n",
"to the client in order to avoid crashing it.\n",
"To change this limit, set the config variable\n",
"`--NotebookApp.iopub_data_rate_limit`.\n",
"\n",
"Current values:\n",
"NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
"NotebookApp.rate_limit_window=3.0 (secs)\n",
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<caption>A matrix: 15 × 1 of type dbl</caption>\n",
"<tbody>\n",
"\t<tr><td>0.7989517</td></tr>\n",
"\t<tr><td>0.8052115</td></tr>\n",
"\t<tr><td>0.8019024</td></tr>\n",
"\t<tr><td>0.8157678</td></tr>\n",
"\t<tr><td>0.7945885</td></tr>\n",
"\t<tr><td>0.8191150</td></tr>\n",
"\t<tr><td>0.8043023</td></tr>\n",
"\t<tr><td>0.8144615</td></tr>\n",
"\t<tr><td>0.8061806</td></tr>\n",
"\t<tr><td>0.8206591</td></tr>\n",
"\t<tr><td>0.8057421</td></tr>\n",
"\t<tr><td>0.7979146</td></tr>\n",
"\t<tr><td>0.8153197</td></tr>\n",
"\t<tr><td>0.8033851</td></tr>\n",
"\t<tr><td>0.8177235</td></tr>\n",
"</tbody>\n",
"</table>\n"
],
"text/latex": [
"A matrix: 15 × 1 of type dbl\n",
"\\begin{tabular}{l}\n",
"\t 0.7989517\\\\\n",
"\t 0.8052115\\\\\n",
"\t 0.8019024\\\\\n",
"\t 0.8157678\\\\\n",
"\t 0.7945885\\\\\n",
"\t 0.8191150\\\\\n",
"\t 0.8043023\\\\\n",
"\t 0.8144615\\\\\n",
"\t 0.8061806\\\\\n",
"\t 0.8206591\\\\\n",
"\t 0.8057421\\\\\n",
"\t 0.7979146\\\\\n",
"\t 0.8153197\\\\\n",
"\t 0.8033851\\\\\n",
"\t 0.8177235\\\\\n",
"\\end{tabular}\n"
],
"text/markdown": [
"\n",
"A matrix: 15 × 1 of type dbl\n",
"\n",
"| 0.7989517 |\n",
"| 0.8052115 |\n",
"| 0.8019024 |\n",
"| 0.8157678 |\n",
"| 0.7945885 |\n",
"| 0.8191150 |\n",
"| 0.8043023 |\n",
"| 0.8144615 |\n",
"| 0.8061806 |\n",
"| 0.8206591 |\n",
"| 0.8057421 |\n",
"| 0.7979146 |\n",
"| 0.8153197 |\n",
"| 0.8033851 |\n",
"| 0.8177235 |\n",
"\n"
],
"text/plain": [
" [,1] \n",
" [1,] 0.7989517\n",
" [2,] 0.8052115\n",
" [3,] 0.8019024\n",
" [4,] 0.8157678\n",
" [5,] 0.7945885\n",
" [6,] 0.8191150\n",
" [7,] 0.8043023\n",
" [8,] 0.8144615\n",
" [9,] 0.8061806\n",
"[10,] 0.8206591\n",
"[11,] 0.8057421\n",
"[12,] 0.7979146\n",
"[13,] 0.8153197\n",
"[14,] 0.8033851\n",
"[15,] 0.8177235"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"number_cl=15\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/15/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:1000) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cl2: 7 7 12 2 5 15 7 10 15 8 13 4 3 7 15 10 2 2 9 14 2 13 10 10 13 8 1 9 10 11 12 15 9 2 12 14 6 11 3 1 5 8 6 2 13 11 5 4 8 7 5 1 1 12 14 15 3 9 5 10 1 13 11 6 5 3 4 6 6 8 3 9 11 6 14 14 7 13 6 4 9 15 13 11 12 11 2 5 3 9 15 14 4 1 1 7 8 12 4 3 \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"IOPub data rate exceeded.\n",
"The notebook server will temporarily stop sending output\n",
"to the client in order to avoid crashing it.\n",
"To change this limit, set the config variable\n",
"`--NotebookApp.iopub_data_rate_limit`.\n",
"\n",
"Current values:\n",
"NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
"NotebookApp.rate_limit_window=3.0 (secs)\n",
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<caption>A matrix: 15 × 1 of type dbl</caption>\n",
"<tbody>\n",
"\t<tr><td>0.7532231</td></tr>\n",
"\t<tr><td>0.7563619</td></tr>\n",
"\t<tr><td>0.7594553</td></tr>\n",
"\t<tr><td>0.7525584</td></tr>\n",
"\t<tr><td>0.7487293</td></tr>\n",
"\t<tr><td>0.7492135</td></tr>\n",
"\t<tr><td>0.7440258</td></tr>\n",
"\t<tr><td>0.7524720</td></tr>\n",
"\t<tr><td>0.7362969</td></tr>\n",
"\t<tr><td>0.7606681</td></tr>\n",
"\t<tr><td>0.7808652</td></tr>\n",
"\t<tr><td>0.7486006</td></tr>\n",
"\t<tr><td>0.7620518</td></tr>\n",
"\t<tr><td>0.7535825</td></tr>\n",
"\t<tr><td>0.7502729</td></tr>\n",
"</tbody>\n",
"</table>\n"
],
"text/latex": [
"A matrix: 15 × 1 of type dbl\n",
"\\begin{tabular}{l}\n",
"\t 0.7532231\\\\\n",
"\t 0.7563619\\\\\n",
"\t 0.7594553\\\\\n",
"\t 0.7525584\\\\\n",
"\t 0.7487293\\\\\n",
"\t 0.7492135\\\\\n",
"\t 0.7440258\\\\\n",
"\t 0.7524720\\\\\n",
"\t 0.7362969\\\\\n",
"\t 0.7606681\\\\\n",
"\t 0.7808652\\\\\n",
"\t 0.7486006\\\\\n",
"\t 0.7620518\\\\\n",
"\t 0.7535825\\\\\n",
"\t 0.7502729\\\\\n",
"\\end{tabular}\n"
],
"text/markdown": [
"\n",
"A matrix: 15 × 1 of type dbl\n",
"\n",
"| 0.7532231 |\n",
"| 0.7563619 |\n",
"| 0.7594553 |\n",
"| 0.7525584 |\n",
"| 0.7487293 |\n",
"| 0.7492135 |\n",
"| 0.7440258 |\n",
"| 0.7524720 |\n",
"| 0.7362969 |\n",
"| 0.7606681 |\n",
"| 0.7808652 |\n",
"| 0.7486006 |\n",
"| 0.7620518 |\n",
"| 0.7535825 |\n",
"| 0.7502729 |\n",
"\n"
],
"text/plain": [
" [,1] \n",
" [1,] 0.7532231\n",
" [2,] 0.7563619\n",
" [3,] 0.7594553\n",
" [4,] 0.7525584\n",
" [5,] 0.7487293\n",
" [6,] 0.7492135\n",
" [7,] 0.7440258\n",
" [8,] 0.7524720\n",
" [9,] 0.7362969\n",
"[10,] 0.7606681\n",
"[11,] 0.7808652\n",
"[12,] 0.7486006\n",
"[13,] 0.7620518\n",
"[14,] 0.7535825\n",
"[15,] 0.7502729"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"number_cl=15\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/15/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:1000) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cl2: 7 7 12 2 5 15 7 10 15 8 13 4 3 7 15 10 2 2 9 14 2 13 10 10 13 8 1 9 10 11 12 15 9 2 12 14 6 11 3 1 5 8 6 2 13 11 5 4 8 7 5 1 1 12 14 15 3 9 5 10 1 13 11 6 5 3 4 6 6 8 3 9 11 6 14 14 7 13 6 4 9 15 13 11 12 11 2 5 3 9 15 14 4 1 1 7 8 12 4 3 \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"IOPub data rate exceeded.\n",
"The notebook server will temporarily stop sending output\n",
"to the client in order to avoid crashing it.\n",
"To change this limit, set the config variable\n",
"`--NotebookApp.iopub_data_rate_limit`.\n",
"\n",
"Current values:\n",
"NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
"NotebookApp.rate_limit_window=3.0 (secs)\n",
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<caption>A matrix: 15 × 1 of type dbl</caption>\n",
"<tbody>\n",
"\t<tr><td>0.7940330</td></tr>\n",
"\t<tr><td>0.8056647</td></tr>\n",
"\t<tr><td>0.7995865</td></tr>\n",
"\t<tr><td>0.7820629</td></tr>\n",
"\t<tr><td>0.7863840</td></tr>\n",
"\t<tr><td>0.7954261</td></tr>\n",
"\t<tr><td>0.7985005</td></tr>\n",
"\t<tr><td>0.7922929</td></tr>\n",
"\t<tr><td>0.7948400</td></tr>\n",
"\t<tr><td>0.8013052</td></tr>\n",
"\t<tr><td>0.8022179</td></tr>\n",
"\t<tr><td>0.7860330</td></tr>\n",
"\t<tr><td>0.8102876</td></tr>\n",
"\t<tr><td>0.7921890</td></tr>\n",
"\t<tr><td>0.7864014</td></tr>\n",
"</tbody>\n",
"</table>\n"
],
"text/latex": [
"A matrix: 15 × 1 of type dbl\n",
"\\begin{tabular}{l}\n",
"\t 0.7940330\\\\\n",
"\t 0.8056647\\\\\n",
"\t 0.7995865\\\\\n",
"\t 0.7820629\\\\\n",
"\t 0.7863840\\\\\n",
"\t 0.7954261\\\\\n",
"\t 0.7985005\\\\\n",
"\t 0.7922929\\\\\n",
"\t 0.7948400\\\\\n",
"\t 0.8013052\\\\\n",
"\t 0.8022179\\\\\n",
"\t 0.7860330\\\\\n",
"\t 0.8102876\\\\\n",
"\t 0.7921890\\\\\n",
"\t 0.7864014\\\\\n",
"\\end{tabular}\n"
],
"text/markdown": [
"\n",
"A matrix: 15 × 1 of type dbl\n",
"\n",
"| 0.7940330 |\n",
"| 0.8056647 |\n",
"| 0.7995865 |\n",
"| 0.7820629 |\n",
"| 0.7863840 |\n",
"| 0.7954261 |\n",
"| 0.7985005 |\n",
"| 0.7922929 |\n",
"| 0.7948400 |\n",
"| 0.8013052 |\n",
"| 0.8022179 |\n",
"| 0.7860330 |\n",
"| 0.8102876 |\n",
"| 0.7921890 |\n",
"| 0.7864014 |\n",
"\n"
],
"text/plain": [
" [,1] \n",
" [1,] 0.7940330\n",
" [2,] 0.8056647\n",
" [3,] 0.7995865\n",
" [4,] 0.7820629\n",
" [5,] 0.7863840\n",
" [6,] 0.7954261\n",
" [7,] 0.7985005\n",
" [8,] 0.7922929\n",
" [9,] 0.7948400\n",
"[10,] 0.8013052\n",
"[11,] 0.8022179\n",
"[12,] 0.7860330\n",
"[13,] 0.8102876\n",
"[14,] 0.7921890\n",
"[15,] 0.7864014"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"number_cl=15\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/15/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:1000) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cl2: 7 7 12 2 5 15 7 10 15 8 13 4 3 7 15 10 2 2 9 14 2 13 10 10 13 8 1 9 10 11 12 15 9 2 12 14 6 11 3 1 5 8 6 2 13 11 5 4 8 7 5 1 1 12 14 15 3 9 5 10 1 13 11 6 5 3 4 6 6 8 3 9 11 6 14 14 7 13 6 4 9 15 13 11 12 11 2 5 3 9 15 14 4 1 1 7 8 12 4 3 \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"IOPub data rate exceeded.\n",
"The notebook server will temporarily stop sending output\n",
"to the client in order to avoid crashing it.\n",
"To change this limit, set the config variable\n",
"`--NotebookApp.iopub_data_rate_limit`.\n",
"\n",
"Current values:\n",
"NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
"NotebookApp.rate_limit_window=3.0 (secs)\n",
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<caption>A matrix: 15 × 1 of type dbl</caption>\n",
"<tbody>\n",
"\t<tr><td>0.7365600</td></tr>\n",
"\t<tr><td>0.7399893</td></tr>\n",
"\t<tr><td>0.7380597</td></tr>\n",
"\t<tr><td>0.7495614</td></tr>\n",
"\t<tr><td>0.7558608</td></tr>\n",
"\t<tr><td>0.7513054</td></tr>\n",
"\t<tr><td>0.7519942</td></tr>\n",
"\t<tr><td>0.7433741</td></tr>\n",
"\t<tr><td>0.7291959</td></tr>\n",
"\t<tr><td>0.7450379</td></tr>\n",
"\t<tr><td>0.7317692</td></tr>\n",
"\t<tr><td>0.7382499</td></tr>\n",
"\t<tr><td>0.7398166</td></tr>\n",
"\t<tr><td>0.7516091</td></tr>\n",
"\t<tr><td>0.7268284</td></tr>\n",
"</tbody>\n",
"</table>\n"
],
"text/latex": [
"A matrix: 15 × 1 of type dbl\n",
"\\begin{tabular}{l}\n",
"\t 0.7365600\\\\\n",
"\t 0.7399893\\\\\n",
"\t 0.7380597\\\\\n",
"\t 0.7495614\\\\\n",
"\t 0.7558608\\\\\n",
"\t 0.7513054\\\\\n",
"\t 0.7519942\\\\\n",
"\t 0.7433741\\\\\n",
"\t 0.7291959\\\\\n",
"\t 0.7450379\\\\\n",
"\t 0.7317692\\\\\n",
"\t 0.7382499\\\\\n",
"\t 0.7398166\\\\\n",
"\t 0.7516091\\\\\n",
"\t 0.7268284\\\\\n",
"\\end{tabular}\n"
],
"text/markdown": [
"\n",
"A matrix: 15 × 1 of type dbl\n",
"\n",
"| 0.7365600 |\n",
"| 0.7399893 |\n",
"| 0.7380597 |\n",
"| 0.7495614 |\n",
"| 0.7558608 |\n",
"| 0.7513054 |\n",
"| 0.7519942 |\n",
"| 0.7433741 |\n",
"| 0.7291959 |\n",
"| 0.7450379 |\n",
"| 0.7317692 |\n",
"| 0.7382499 |\n",
"| 0.7398166 |\n",
"| 0.7516091 |\n",
"| 0.7268284 |\n",
"\n"
],
"text/plain": [
" [,1] \n",
" [1,] 0.7365600\n",
" [2,] 0.7399893\n",
" [3,] 0.7380597\n",
" [4,] 0.7495614\n",
" [5,] 0.7558608\n",
" [6,] 0.7513054\n",
" [7,] 0.7519942\n",
" [8,] 0.7433741\n",
" [9,] 0.7291959\n",
"[10,] 0.7450379\n",
"[11,] 0.7317692\n",
"[12,] 0.7382499\n",
"[13,] 0.7398166\n",
"[14,] 0.7516091\n",
"[15,] 0.7268284"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"number_cl=15\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/15/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/15/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:1000) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cl2: 7 7 12 2 5 15 7 10 15 8 13 4 3 7 15 10 2 2 9 14 2 13 10 10 13 8 1 9 10 11 12 15 9 2 12 14 6 11 3 1 5 8 6 2 13 11 5 4 8 7 5 1 1 12 14 15 3 9 5 10 1 13 11 6 5 3 4 6 6 8 3 9 11 6 14 14 7 13 6 4 9 15 13 11 12 11 2 5 3 9 15 14 4 1 1 7 8 12 4 3 \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"IOPub data rate exceeded.\n",
"The notebook server will temporarily stop sending output\n",
"to the client in order to avoid crashing it.\n",
"To change this limit, set the config variable\n",
"`--NotebookApp.iopub_data_rate_limit`.\n",
"\n",
"Current values:\n",
"NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
"NotebookApp.rate_limit_window=3.0 (secs)\n",
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<caption>A matrix: 15 × 1 of type dbl</caption>\n",
"<tbody>\n",
"\t<tr><td>0.4727026</td></tr>\n",
"\t<tr><td>0.4756525</td></tr>\n",
"\t<tr><td>0.4718643</td></tr>\n",
"\t<tr><td>0.4635589</td></tr>\n",
"\t<tr><td>0.4793765</td></tr>\n",
"\t<tr><td>0.4613873</td></tr>\n",
"\t<tr><td>0.4629963</td></tr>\n",
"\t<tr><td>0.4653092</td></tr>\n",
"\t<tr><td>0.4717958</td></tr>\n",
"\t<tr><td>0.4745232</td></tr>\n",
"\t<tr><td>0.4752839</td></tr>\n",
"\t<tr><td>0.4738429</td></tr>\n",
"\t<tr><td>0.4763239</td></tr>\n",
"\t<tr><td>0.4642153</td></tr>\n",
"\t<tr><td>0.4669012</td></tr>\n",
"</tbody>\n",
"</table>\n"
],
"text/latex": [
"A matrix: 15 × 1 of type dbl\n",
"\\begin{tabular}{l}\n",
"\t 0.4727026\\\\\n",
"\t 0.4756525\\\\\n",
"\t 0.4718643\\\\\n",
"\t 0.4635589\\\\\n",
"\t 0.4793765\\\\\n",
"\t 0.4613873\\\\\n",
"\t 0.4629963\\\\\n",
"\t 0.4653092\\\\\n",
"\t 0.4717958\\\\\n",
"\t 0.4745232\\\\\n",
"\t 0.4752839\\\\\n",
"\t 0.4738429\\\\\n",
"\t 0.4763239\\\\\n",
"\t 0.4642153\\\\\n",
"\t 0.4669012\\\\\n",
"\\end{tabular}\n"
],
"text/markdown": [
"\n",
"A matrix: 15 × 1 of type dbl\n",
"\n",
"| 0.4727026 |\n",
"| 0.4756525 |\n",
"| 0.4718643 |\n",
"| 0.4635589 |\n",
"| 0.4793765 |\n",
"| 0.4613873 |\n",
"| 0.4629963 |\n",
"| 0.4653092 |\n",
"| 0.4717958 |\n",
"| 0.4745232 |\n",
"| 0.4752839 |\n",
"| 0.4738429 |\n",
"| 0.4763239 |\n",
"| 0.4642153 |\n",
"| 0.4669012 |\n",
"\n"
],
"text/plain": [
" [,1] \n",
" [1,] 0.4727026\n",
" [2,] 0.4756525\n",
" [3,] 0.4718643\n",
" [4,] 0.4635589\n",
" [5,] 0.4793765\n",
" [6,] 0.4613873\n",
" [7,] 0.4629963\n",
" [8,] 0.4653092\n",
" [9,] 0.4717958\n",
"[10,] 0.4745232\n",
"[11,] 0.4752839\n",
"[12,] 0.4738429\n",
"[13,] 0.4763239\n",
"[14,] 0.4642153\n",
"[15,] 0.4669012"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"number_cl=15\n",
"ind <- 0\n",
"JI_final <- matrix(data=NA, nrow=number_cl, ncol=1)\n",
"#cat(JI_final,\"\\n\")\n",
"# Read clusters imposed on simulated data \n",
"cl <- as.matrix(read.table(\"../data/simulations_20210329212141/equal/15/clusters.txt\", \n",
" sep=\"\\t\", row.names=1, header=TRUE))\n",
"#cat(\"cl:\",cl,\"\\t\")\n",
"cl2 <- as.matrix(as.numeric(cl[,2]))\n",
"cat(\"cl2:\",cl2[,1],\"\\n\")\n",
"rownames(cl2) <- cl[,1]\n",
"\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/AE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FAETC_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/DAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"#factorization=read.table(\"../data/simulations_20210329212141/equal/15/VAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"factorization=read.table(\"../data/simulations_20210329212141/equal/15/LSTMVAE_FCTAE_EM.txt\", sep=\" \", row.names=cl[,1],header=FALSE)\n",
"\n",
"\n",
"\n",
"factors <- factorization\n",
"#factors <- factorizations[[i]][[1]]\n",
"\n",
"#print(factors)\n",
"# Clustering by Kmeans\n",
"JI_good <- numeric(0)\n",
"for (run in 1:1000) {\n",
"kmeans.out <- kmeans(factors, centers=number_cl) \n",
"clust_iCluster <- as.matrix(kmeans.out$cluster)\n",
"cat(\"clust_iCluster:\",clust_iCluster,\"\\n\")\n",
"######creation sets of samples\n",
"JI_mat <- numeric(0)\n",
"for (p in 1:number_cl) {\n",
" x1 <- rownames(clust_iCluster)[which(clust_iCluster[,1]==p)]\n",
" print(x1)\n",
"\n",
" row <- numeric(0)\n",
" for(j in 1:number_cl) {\n",
" x2 <- rownames(cl2)[which(cl2[,1]==j)]\n",
" cat(\"x2:\",x2,\"\\n\")\n",
" I <- length(intersect(x1,x2))#交集\n",
" cat(\"I:\",I,\"\\n\")\n",
" S <- I/(length(x1)+length(x2)-I)\n",
" cat(\"S:\",S,\"\\n\")\n",
" row <- cbind(row,S)\n",
" cat(\"row:\",row,\"\\n\")\n",
" }\n",
" JI_mat <- rbind(JI_mat,row)\n",
" cat(\"JI_mat:\",JI_mat,\"\\n\")\n",
" print(JI_mat)\n",
"\n",
"\n",
" }\n",
" JI_good <- rbind(JI_good,apply(JI_mat,1,max))\n",
" cat(\"JI_good:\",JI_good,\"\\n\")\n",
"}\n",
"JI_final[1:number_cl] <- apply(JI_good,2,mean)\n",
"JI_final"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "R",
"language": "R",
"name": "ir"
},
"language_info": {
"codemirror_mode": "r",
"file_extension": ".r",
"mimetype": "text/x-r-source",
"name": "R",
"pygments_lexer": "r",
"version": "3.5.1"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Datasets
Models
