Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Subregion analysis for GPS data #44

Merged
merged 18 commits into from May 4, 2021
Merged

Subregion analysis for GPS data #44

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
fc208c3
add functionality of (1) where user can now perform subregion analysi…
aliu22 Apr 20, 2021
ac202e4
give path for subregions shapefile in comments
aliu22 Apr 20, 2021
56b08f6
Merge branch 'master' into geo_part2
aliu22 Apr 22, 2021
9505ad3
added region_labels functionality, subregion analysis for gps, renami…
aliu22 Apr 27, 2021
d6e5343
update YFCC
aliu22 Apr 27, 2021
78cd536
Merge branch 'master' into geo_part2
aliu22 Apr 27, 2021
b4da2db
testing and minor fixes
aliu22 Apr 29, 2021
ffd84fa
readme
aliu22 Apr 29, 2021
a873540
reaadd commented out scenemapping
aliu22 Apr 29, 2021
a12ef8a
automate distinction between country and region labels
aliu22 Apr 29, 2021
69e9232
bug fix
aliu22 Apr 29, 2021
aaf6d58
README change
aliu22 Apr 29, 2021
9cee230
readme rewording
aliu22 May 2, 2021
9c9c6c2
refactor 6a and 6b to geo_tag as per new naming convention
aliu22 May 2, 2021
97eee74
add elif instead of if for readability
aliu22 May 2, 2021
08f1dd8
add new gps and redirection changes to prerun as well
aliu22 May 2, 2021
03f7131
rename all .pkl files to geo_ctr or geo_tag
aliu22 May 4, 2021
e1618ca
change pkl file name in prerun as well
aliu22 May 4, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Expand Up @@ -81,7 +81,7 @@ geo_tag: Counts the number of tags from each region, as well as extracts AlexNet

geo_lng: Counts the languages that make up the image tags, and whether or not they are local to the country the image is from. Also extracts image-level features to compare if locals and tourist portray a country differently

Note: Geography-Based analyses require a mapping from images to location. The 2 primary ways we've encountered these mappings in existing datasets are geography labels (ie. String formatted locations like 'Manhattan'), and GPS labels (latitude and longitude coordinate pairs). Our analyses supports both types of geography mappings. Namely, the user should specify in their dataset class the `geography_info_type` to be one of the following:
Note: Geography-Based analyses require a mapping from images to location. The 2 formats of geography annotations supported are (ie. String formatted locations like 'Manhattan'), and GPS labels (latitude and longitude coordinate pairs). Namely, the user should specify in their dataset class the `geography_info_type` to be one of the following:
- 'GPS_LABEL': datasets with mappings from image to GPS coordinates
- 'STRING_FORMATTED_LABEL', datasets with mappings from image to string-formatted labels

Expand Down
38 changes: 18 additions & 20 deletions analysis_notebooks/Geography Analysis.ipynb
View file
Open in desktop
Expand Up @@ -724,8 +724,8 @@
"outputs": [],
"source": [
"if (dataset.geography_info_type == \"STRING_FORMATTED_LABEL\" and dataset.geography_label_string_type == \"COUNTRY_LABEL\"):\n",
" if not os.path.exists(\"results/{0}/6\".format(folder_name)):\n",
" os.mkdir(\"results/{0}/6\".format(folder_name))\n",
" if not os.path.exists(\"results/{0}/geo_tag\".format(folder_name)):\n",
" os.mkdir(\"results/{0}/geo_tag\".format(folder_name))\n",
" info_stats = pickle.load(open(\"results/{}/geo_tag.pkl\".format(folder_name), \"rb\")) #20GB\n",
" country_tags = info_stats['country_tags']\n",
" tag_to_subregion_features = info_stats['tag_to_subregion_features']\n",
Expand All @@ -741,7 +741,7 @@
" subregion_tags[subregion] = np.add(subregion_tags[subregion], counts)\n",
" total_counts = total_counts.astype(int)\n",
" sum_total_counts = int(np.sum(total_counts))\n",
" if not os.path.exists('checkpoints/{}/6_a.pkl'.format(folder_name)):\n",
" if not os.path.exists('checkpoints/{}/geo_tag_a.pkl'.format(folder_name)):\n",
" pvalues_over = {} # pvalue : '[country]: [tag] (country num and total num info for now)'\n",
" pvalues_under = {} \n",
" for country, counts in country_tags.items():\n",
Expand All @@ -760,7 +760,7 @@
" else:\n",
" pvalues_under[p] = tag_info\n",
" else:\n",
" pvalues_under, pvalues_over = pickle.load(open('checkpoints/{}/6_a.pkl'.format(folder_name), 'rb'))\n",
" pvalues_under, pvalues_over = pickle.load(open('checkpoints/{}/geo_tag_a.pkl'.format(folder_name), 'rb'))\n",
" subregion_pvalues_over = {}\n",
" subregion_pvalues_under = {}\n",
" for subregion, counts in subregion_tags.items():\n",
Expand All @@ -778,9 +778,8 @@
" subregion_pvalues_under[p] = tag_info\n",
" \n",
"elif (dataset.geography_info_type == \"STRING_FORMATTED_LABEL\" and dataset.geography_label_string_type == \"REGION_LABEL\"):\n",
" print(\"Geo_tag work for region label formatted dataset\")\n",
" if not os.path.exists(\"results/{0}/6\".format(folder_name)):\n",
" os.mkdir(\"results/{0}/6\".format(folder_name))\n",
" if not os.path.exists(\"results/{0}/geo_tag\".format(folder_name)):\n",
" os.mkdir(\"results/{0}/geo_tag\".format(folder_name))\n",
" info_stats = pickle.load(open(\"results/{}/geo_tag_region.pkl\".format(folder_name), \"rb\")) #20GB\n",
" region_tags = info_stats['region_tags']\n",
" tag_to_region_features = info_stats['tag_to_region_features']\n",
Expand All @@ -794,7 +793,7 @@
" total_counts = total_counts.astype(int)\n",
" sum_total_counts = int(np.sum(total_counts))\n",
"\n",
" if not os.path.exists('checkpoints/{}/6_a.pkl'.format(folder_name)):\n",
" if not os.path.exists('checkpoints/{}/geo_tag_a.pkl'.format(folder_name)):\n",
" pvalues_over = {} # pvalue : '[region]: [tag] (region num and total num info for now)'\n",
" pvalues_under = {} \n",
" for region, counts in region_tags.items():\n",
Expand All @@ -813,12 +812,11 @@
" else:\n",
" pvalues_under[p] = tag_info\n",
" else:\n",
" pvalues_under, pvalues_over = pickle.load(open('checkpoints/{}/6_a.pkl'.format(folder_name), 'rb'))\n",
" pvalues_under, pvalues_over = pickle.load(open('checkpoints/{}/geo_tag_a.pkl'.format(folder_name), 'rb'))\n",
"\n",
"elif dataset.geography_info_type == \"GPS_LABEL\":\n",
" print(\"Geo_tag work for gps formatted dataset\")\n",
" if not os.path.exists(\"results/{0}/6\".format(folder_name)):\n",
" os.mkdir(\"results/{0}/6\".format(folder_name))\n",
" if not os.path.exists(\"results/{0}/geo_tag\".format(folder_name)):\n",
" os.mkdir(\"results/{0}/geo_tag\".format(folder_name))\n",
" info_stats = pickle.load(open(\"results/{}/geo_tag_gps.pkl\".format(folder_name), \"rb\")) #20GB\n",
" region_tags = info_stats['region_tags']\n",
" subregion_tags = info_stats.get('subregion_tags', None)\n",
Expand All @@ -833,7 +831,7 @@
" total_counts = total_counts.astype(int)\n",
" sum_total_counts = int(np.sum(total_counts))\n",
"\n",
" if not os.path.exists('checkpoints/{}/6_a.pkl'.format(folder_name)):\n",
" if not os.path.exists('checkpoints/{}/geo_tag_a.pkl'.format(folder_name)):\n",
" pvalues_over = {} # pvalue : '[region]: [tag] (region num and total num info for now)'\n",
" pvalues_under = {} \n",
" for region, counts in region_tags.items():\n",
Expand All @@ -852,7 +850,7 @@
" else:\n",
" pvalues_under[p] = tag_info\n",
" else:\n",
" pvalues_under, pvalues_over = pickle.load(open('checkpoints/{}/6_a.pkl'.format(folder_name), 'rb'))\n",
" pvalues_under, pvalues_over = pickle.load(open('checkpoints/{}/geo_tag_a.pkl'.format(folder_name), 'rb'))\n",
"\n",
" if subregion_tags is not None:\n",
" subregion_total_counts = np.zeros(len(categories))\n",
Expand Down Expand Up @@ -942,7 +940,7 @@
" import warnings\n",
" warnings.filterwarnings(\"ignore\")\n",
"\n",
" if not os.path.exists('checkpoints/{}/6_b.pkl'.format(folder_name)):\n",
" if not os.path.exists('checkpoints/{}/geo_tag_b.pkl'.format(folder_name)):\n",
" phrase_to_value = {}\n",
" # Look at appearance differences in how a tag is represented across subregions\n",
" for tag in tag_to_subregion_features.keys():\n",
Expand Down Expand Up @@ -988,7 +986,7 @@
" fontP = FontProperties()\n",
" fontP.set_size('small')\n",
" lgd = plt.legend(handles=handles, bbox_to_anchor=(1.04,1), loc=\"upper left\", prop=fontP)\n",
" plt.savefig('results/{0}/{1}/{2}_tsne.png'.format(folder_name, 6, dataset.categories[tag]), bbox_extra_artists=(lgd,), bbox_inches='tight')\n",
" plt.savefig('results/{0}/{1}/{2}_tsne.png'.format(folder_name, \"geo_tag\", dataset.categories[tag]), bbox_extra_artists=(lgd,), bbox_inches='tight')\n",
" plt.close()\n",
"\n",
" class_preds = clf.predict(all_features)\n",
Expand Down Expand Up @@ -1034,10 +1032,10 @@
" phrase = dataset.labels_to_names[dataset.categories[tag]]\n",
" phrase_to_value[phrase] = [value, all_subregions[diff_subregion], acc, p_value, num_features, j_to_acc]\n",
" \n",
" pickle.dump([original_labels, class_probs, class_preds, diff_subregion, all_filepaths], open('results/{0}/{1}/{2}_info.pkl'.format(folder_name, 6, dataset.labels_to_names[dataset.categories[tag]]), 'wb'))\n",
" pickle.dump(phrase_to_value, open('checkpoints/{}/6_b.pkl'.format(folder_name), 'wb'))\n",
" pickle.dump([original_labels, class_probs, class_preds, diff_subregion, all_filepaths], open('results/{0}/{1}/{2}_info.pkl'.format(folder_name, \"geo_tag\", dataset.labels_to_names[dataset.categories[tag]]), 'wb'))\n",
" pickle.dump(phrase_to_value, open('checkpoints/{}/geo_tag_b.pkl'.format(folder_name), 'wb'))\n",
" else:\n",
" phrase_to_value = pickle.load(open('checkpoints/{}/6_b.pkl'.format(folder_name), 'rb'))\n",
" phrase_to_value = pickle.load(open('checkpoints/{}/geo_tag_b.pkl'.format(folder_name), 'rb'))\n",
"\n",
" svm_options = []\n",
" best_tag = None\n",
Expand All @@ -1055,7 +1053,7 @@
" else:\n",
" if tag is None:\n",
" return\n",
" this_info = pickle.load(open('results/{0}/{1}/{2}_info.pkl'.format(folder_name, 6, tag), 'rb'))\n",
" this_info = pickle.load(open('results/{0}/{1}/{2}_info.pkl'.format(folder_name, \"geo_tag\", tag), 'rb'))\n",
" labels, class_probs, class_preds, diff_subregion, all_filepaths = this_info\n",
" value, region, acc, p_value, num_features, j_to_acc = phrase_to_value[tag]\n",
" if num is not None:\n",
Expand Down
2 changes: 1 addition & 1 deletion measurements/geography_based.py
View file
Open in desktop
Expand Up @@ -173,7 +173,7 @@ def geo_tag(dataloader, args):
if (dataloader.dataset.geography_info_type == "GPS_LABEL"):
print("redirecting to geo_tag_gps()...")
return geo_tag_gps(dataloader, args)
if (dataloader.dataset.geography_info_type == "STRING_FORMATTED_LABEL" and dataloader.dataset.geography_label_string_type == "REGION_LABEL"):
elif (dataloader.dataset.geography_info_type == "STRING_FORMATTED_LABEL" and dataloader.dataset.geography_label_string_type == "REGION_LABEL"):
print("redirecting to geo_tag_region()...")
return geo_tag_region(dataloader, args)
country_tags = {}
Expand Down