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

task 9

Browse Source
This commit is contained in:
pranavbrkr 2023-10-14 17:53:15 -07:00
parent b117bc84e8
commit 72c65b7899
2 changed files with 68 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
Phase 2/task_9.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 207, "execution_count": 71,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -21,7 +21,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 208, "execution_count": 72,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -35,7 +35,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 209, "execution_count": 73,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -45,14 +45,14 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 210, "execution_count": 74,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"cm_fd-cp-10-semantics.json loaded\n" "image_sim-cm_fd-lda-10-model.joblib loaded\n"
] ]
} }
], ],
@ -88,6 +88,15 @@
"\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",
@ -100,16 +109,24 @@
" 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",
" else:\n", " else:\n",
" print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json does not exist\")\n" " print(f\"{selected_latent_space}-{selected_feature_model}-{selected_dim_reduction_method}-{k}-semantics.json does not exist\")"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 211, "execution_count": 75,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -169,10 +186,18 @@
" label_vectors.append(sim_matrix[i])\n", " label_vectors.append(sim_matrix[i])\n",
" label_rep = [sum(col) / len(col) for col in zip(*label_vectors)]\n", " label_rep = [sum(col) / len(col) for col in zip(*label_vectors)]\n",
"\n", "\n",
"\n",
" for centroid in S:\n", " for centroid in S:\n",
" comparison_vector.append(math.dist(label_rep, centroid))\n", " comparison_vector.append(math.dist(label_rep, centroid))\n",
"\n", "\n",
" case \"lda\":\n",
" comparison_feature_space = np.array(data[\"image-semantic\"])\n",
" label_vectors = []\n",
" length = len(comparison_feature_space)\n",
" for i in range(length):\n",
" if all_images[i][\"true_label\"] == label:\n",
" label_vectors.append(comparison_feature_space[i])\n",
" comparison_vector = [sum(col) / len(col) for col in zip(*label_vectors)] \n",
"\n",
" n = len(comparison_feature_space)\n", " n = len(comparison_feature_space)\n",
"\n", "\n",
" distances = []\n", " distances = []\n",
@ -200,7 +225,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 233, "execution_count": 76,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -230,7 +255,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 234, "execution_count": 77,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -254,6 +279,11 @@
" comparison_feature_space = np.array(data[\"image-semantic\"])\n", " comparison_feature_space = np.array(data[\"image-semantic\"])\n",
" comparison_vector = comparison_feature_space[label]\n", " comparison_vector = comparison_feature_space[label]\n",
"\n", "\n",
" case \"lda\":\n",
" comparison_feature_space = np.array(data[\"image-semantic\"])\n",
" comparison_vector = comparison_feature_space[label] \n",
"\n",
"\n",
" n = len(comparison_feature_space)\n", " n = len(comparison_feature_space)\n",
" distances = []\n", " distances = []\n",
" for i in range(n):\n", " for i in range(n):\n",
@ -268,23 +298,23 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 235, "execution_count": 78,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"{'label': 2, 'distance': 0.9999999999999999}\n", "{'image_id': 2641, 'label': 46, 'distance': 0.013618215122607105}\n",
"{'label': 4, 'distance': 0.9999999999999999}\n", "{'image_id': 1686, 'label': 16, 'distance': 0.015215365128880378}\n",
"{'label': 6, 'distance': 0.9999999999999999}\n", "{'image_id': 2310, 'label': 35, 'distance': 0.015383486193179943}\n",
"{'label': 7, 'distance': 0.9999999999999999}\n", "{'image_id': 3781, 'label': 84, 'distance': 0.01541886635507712}\n",
"{'label': 8, 'distance': 0.9999999999999999}\n", "{'image_id': 1483, 'label': 11, 'distance': 0.015474891099448796}\n",
"{'label': 9, 'distance': 0.9999999999999999}\n", "{'image_id': 2719, 'label': 48, 'distance': 0.01960489858697963}\n",
"{'label': 10, 'distance': 0.9999999999999999}\n", "{'image_id': 3787, 'label': 85, 'distance': 0.02006387165132467}\n",
"{'label': 11, 'distance': 0.9999999999999999}\n", "{'image_id': 3877, 'label': 87, 'distance': 0.02050382578938892}\n",
"{'label': 13, 'distance': 0.9999999999999999}\n", "{'image_id': 3719, 'label': 82, 'distance': 0.02293235381986182}\n",
"{'label': 14, 'distance': 0.9999999999999999}\n" "{'image_id': 3403, 'label': 70, 'distance': 0.024912695992711693}\n"
] ]
} }
], ],
@ -303,6 +333,13 @@
"\n", "\n",
" extract_similarities_ls2(data, label)\n" " extract_similarities_ls2(data, label)\n"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {

2
Phase 2/utils.py
View File

@ -1132,7 +1132,7 @@ def extract_latent_semantics_from_sim_matrix(
dump( dump(
model, model,
f"{sim_type}-{feature_model}-{dim_reduction_method}-{k}-model.joblib", f"{sim_type}_sim-{feature_model}-{dim_reduction_method}-{k}-model.joblib",
) )
# for each latent semantic, sort object-weight pairs by weights in descending order # for each latent semantic, sort object-weight pairs by weights in descending order