my-asu-archive/CSE515_MWDB_Project
1
0
Fork 0
mirror of https://github.com/20kaushik02/CSE515_MWDB_Project.git synced 2025-12-06 11:04:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

task7 lda

Browse Source
This commit is contained in:
pranavbrkr 2023-10-14 16:49:50 -07:00
parent 6adc8bcf70
commit 579c68f9fa
1 changed files with 71 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
Phase 2/task_7.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 49, "execution_count": 102,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -21,7 +21,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 50, "execution_count": 103,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -36,7 +36,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 51, "execution_count": 104,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -46,14 +46,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 52, "execution_count": 105,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"image_sim-cm_fd-kmeans-10-semantics.json loaded\n" "label_sim-cm_fd-lda-10-model.joblib loaded\n"
] ]
} }
], ],
@ -87,6 +87,15 @@
"\n", "\n",
"match selected_latent_space:\n", "match selected_latent_space:\n",
" case \"\":\n", " case \"\":\n",
" if selected_dim_reduction_method == \"lda\":\n",
" if os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\") and os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
" if os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\"):\n",
" model = load(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\")\n",
" data = json.load(open(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
" print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib and json loaded\")\n",
" else:\n",
" print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib does not exist\")\n",
" else:\n",
" if os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n", " if os.path.exists(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
" data = json.load(open(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n", " data = json.load(open(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
" print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json loaded\")\n", " print(f\"{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json loaded\")\n",
@ -99,6 +108,14 @@
" else:\n", " else:\n",
" print(f\"{selected_feature_model}-cp-{k}-semantics.json does not exist\")\n", " print(f\"{selected_feature_model}-cp-{k}-semantics.json does not exist\")\n",
" case _:\n", " case _:\n",
" if selected_dim_reduction_method == \"lda\":\n",
" if os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\") and os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
" model = load(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib\")\n",
" data = json.load(open(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
" print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib loaded\")\n",
" else:\n",
" print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-model.joblib does not exist\")\n",
" else:\n",
" if os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n", " if os.path.exists(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"):\n",
" data = json.load(open(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n", " data = json.load(open(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json\"))\n",
" print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json loaded\")\n", " print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json loaded\")\n",
@ -108,7 +125,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 53, "execution_count": 106,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -153,6 +170,19 @@
" else:\n", " else:\n",
" comparison_vector.append(math.dist(image_fd, centroid))\n", " comparison_vector.append(math.dist(image_fd, centroid))\n",
" \n", " \n",
" case \"lda\":\n",
" comparison_feature_space = np.array(data[\"image-semantic\"])\n",
" if latent_space == \"image_sim\":\n",
" comparison_vector = comparison_feature_space[int(image_id / 2)]\n",
" else:\n",
" fd = np.array(all_images[int(image_id / 2)][selected_feature_model])\n",
" min_value = np.min(fd)\n",
" feature_vectors_shifted = fd - min_value\n",
" comparison_vector = model.transform(feature_vectors_shifted.flatten().reshape(1, -1)).flatten()\n",
" print(comparison_feature_space.shape)\n",
" print(comparison_vector.shape)\n",
" # print(retValue)\n",
"\n",
" n = len(comparison_feature_space)\n", " n = len(comparison_feature_space)\n",
"\n", "\n",
" distances = []\n", " distances = []\n",
@ -168,7 +198,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 54, "execution_count": 107,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -198,7 +228,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 55, "execution_count": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -224,6 +254,10 @@
" comparison_feature_space = np.array(data[\"image-semantic\"])\n", " comparison_feature_space = np.array(data[\"image-semantic\"])\n",
" comparison_vector = comparison_feature_space[img_label]\n", " comparison_vector = comparison_feature_space[img_label]\n",
"\n", "\n",
" case \"lda\":\n",
" comparison_feature_space = np.array(data[\"image-semantic\"])\n",
" comparison_vector = comparison_feature_space[img_label]\n",
"\n",
" n = len(comparison_feature_space)\n", " n = len(comparison_feature_space)\n",
" distance = float('inf')\n", " distance = float('inf')\n",
" most_similar_label = img_label\n", " most_similar_label = img_label\n",
@ -244,23 +278,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 56, "execution_count": 109,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"{'image_id': 2457, 'label': 39, 'distance': 5.400083378408386}\n", "Most similar label to 0 is 19\n",
"{'image_id': 2629, 'label': 46, 'distance': 6.360136822031199}\n", "3634\n",
"{'image_id': 1916, 'label': 23, 'distance': 8.279651870400942}\n", "3600\n",
"{'image_id': 1975, 'label': 24, 'distance': 9.305370097143731}\n", "3562\n",
"{'image_id': 3287, 'label': 65, 'distance': 9.696792665660324}\n", "3618\n",
"{'image_id': 292, 'label': 1, 'distance': 10.198675122162054}\n", "3574\n",
"{'image_id': 3965, 'label': 90, 'distance': 11.544874878013612}\n", "3604\n",
"{'image_id': 4018, 'label': 92, 'distance': 12.064116415014514}\n", "3550\n",
"{'image_id': 4037, 'label': 92, 'distance': 13.383239007317492}\n", "3542\n",
"{'image_id': 4307, 'label': 99, 'distance': 14.448284626506538}\n" "3564\n",
"3538\n"
] ]
} }
], ],
@ -279,6 +314,13 @@
"\n", "\n",
" extract_similarities_ls2(data, image_id)\n" " extract_similarities_ls2(data, image_id)\n"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {