diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..311511eadbffae7d65e05cea9fecfc40cbbf28f6
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,4 @@
+*.csv filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
+*_index filter=lfs diff=lfs merge=lfs -text
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..c8a0beb57948f69b138009708ca721945420b578
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,135 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
\ No newline at end of file
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A.csv b/FR_RESULTS/FR.txt_100_4_0.002__A.csv
new file mode 100644
index 0000000000000000000000000000000000000000..e324738614f3b1bcc576cfab0df3b078253da80e
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee150c565e634ea19f7bea66ef9548fb8dd0fb49eb8dcffd9cc47d13483b6003
+size 21477
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A.h5 b/FR_RESULTS/FR.txt_100_4_0.002__A.h5
new file mode 100644
index 0000000000000000000000000000000000000000..1775466713e86e176f6e7d4cd8aa567771f0d336
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f657821ce36e21747dbaeeafb25adb79e4b81d592529b1b77db29f5006b8949
+size 63516712
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A.json b/FR_RESULTS/FR.txt_100_4_0.002__A.json
new file mode 100644
index 0000000000000000000000000000000000000000..57e99fb82b33c40922e16f16d0fbc430fac55b38
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1e68b2d119da4f8b4f278098c89220bb11e537da6d15c00a22a3a105e14bc0
+size 357
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_C.csv b/FR_RESULTS/FR.txt_100_4_0.002__A_C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..224755496064b168fd20e26fc7c4392c03792445
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f673b4987da0613bb795baa4f66942086aa47d748e64e640bbaf459bc132a7
+size 21424
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_C.h5 b/FR_RESULTS/FR.txt_100_4_0.002__A_C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..f532776dafd038fd5f32abf1e96d2080d15efcae
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfef6a5c72515a611941a363c36af42dc76a736c6f5cde3f24d30116d14eba9
+size 85963816
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_C.json b/FR_RESULTS/FR.txt_100_4_0.002__A_C.json
new file mode 100644
index 0000000000000000000000000000000000000000..f029338231e3856b67818456d5000b88a47b2940
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b8f07cda56786059003e821885337f9ba6e46bbd5883f144f8dcb315ccd44d
+size 364
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_C_index b/FR_RESULTS/FR.txt_100_4_0.002__A_C_index
new file mode 100644
index 0000000000000000000000000000000000000000..c5297f4a6e4811c2eb25f405d9d2574226ec0c57
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32f1d51c54457712159ebb9e6f9e985e61f3f4236521ec9d990d0b24fdb13a5
+size 1060266
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I.csv b/FR_RESULTS/FR.txt_100_4_0.002__A_I.csv
new file mode 100644
index 0000000000000000000000000000000000000000..63261e63a2ef6c78e117d003c3ebee6ba47d7853
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1425c6d13fd52b62c75f6770bf2228f960583579b607a712a9830cc67b01782c
+size 21496
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I.h5 b/FR_RESULTS/FR.txt_100_4_0.002__A_I.h5
new file mode 100644
index 0000000000000000000000000000000000000000..c6bf2ccc1a997b2a15fbfdfa362cd4754c783d66
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a914bbc78c012f941747bcd668efad9ea4aec94a33f5339c7e9474a8864c7bef
+size 63516712
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I.json b/FR_RESULTS/FR.txt_100_4_0.002__A_I.json
new file mode 100644
index 0000000000000000000000000000000000000000..a280c4fcca64a0af3ea3ce0d297f62e933a00fac
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92aae942c9e46852e07a33faf1e953a92f4afd9e2d12d3db24a24097868ab2d1
+size 364
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.csv b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..cb8e7c1e2f8c9eed5d7ee8a9512aa9c9bced9fa9
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5bf71cb4a330d8c058f77d569e9c8a73774faf277cfccbb3fce9ffc96961cc
+size 21444
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.h5 b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..33696062e98a9b6cebac00f17c36163376fcb7af
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e076c21184c090808a6abff1d36bfd190ab567ff2f19bdc59cd2b304e2663c
+size 85963816
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.json b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.json
new file mode 100644
index 0000000000000000000000000000000000000000..35a79c9583be8c9216518bc645923a59795724b4
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7d2485fb2fb411e9f5d2162a6dbf92f683269e69b2bd8f7b1fe012a2d0dcee
+size 371
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I_C_index b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C_index
new file mode 100644
index 0000000000000000000000000000000000000000..c5297f4a6e4811c2eb25f405d9d2574226ec0c57
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I_C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32f1d51c54457712159ebb9e6f9e985e61f3f4236521ec9d990d0b24fdb13a5
+size 1060266
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_I_index b/FR_RESULTS/FR.txt_100_4_0.002__A_I_index
new file mode 100644
index 0000000000000000000000000000000000000000..368383589d1565b9af63d48ff8de24df0b4fc22e
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_I_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39af04607deba9535c5c8db22f8f29575cd8864c1b05f3ae6179132e97366fe6
+size 706706
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__A_index b/FR_RESULTS/FR.txt_100_4_0.002__A_index
new file mode 100644
index 0000000000000000000000000000000000000000..368383589d1565b9af63d48ff8de24df0b4fc22e
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__A_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39af04607deba9535c5c8db22f8f29575cd8864c1b05f3ae6179132e97366fe6
+size 706706
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__C.csv b/FR_RESULTS/FR.txt_100_4_0.002__C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..f7c92b645c8c0a6cd9210ee804a0110df75edf37
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2500b13371c1abfdcb9554cb4557a3007c77ad86e0d4cf29f3539665a2e46e
+size 21425
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__C.h5 b/FR_RESULTS/FR.txt_100_4_0.002__C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..34d4ec3afe932dfb802b4e3514b79e4c6aebf9f2
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d64482b807f900691c9d2adb8683584b1ddc957bcea5fc7f21e761e234df10
+size 85963816
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__C.json b/FR_RESULTS/FR.txt_100_4_0.002__C.json
new file mode 100644
index 0000000000000000000000000000000000000000..7ea696e404c1d778a45da9948212c86180d6965b
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca1390054744e0e3a162294dc57673b1e094675f286c246f1c70b46c9795c73b
+size 357
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__C_index b/FR_RESULTS/FR.txt_100_4_0.002__C_index
new file mode 100644
index 0000000000000000000000000000000000000000..c5297f4a6e4811c2eb25f405d9d2574226ec0c57
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32f1d51c54457712159ebb9e6f9e985e61f3f4236521ec9d990d0b24fdb13a5
+size 1060266
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I.csv b/FR_RESULTS/FR.txt_100_4_0.002__I.csv
new file mode 100644
index 0000000000000000000000000000000000000000..72a5ba577f8d9336b74578bbb78431cedbc98188
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3040479bcb1336ee1634425870ed0d22a30fba9857c83117674a9b229046cf49
+size 21512
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I.h5 b/FR_RESULTS/FR.txt_100_4_0.002__I.h5
new file mode 100644
index 0000000000000000000000000000000000000000..5d1df5079888fa4f4116b8e3c686172d4db74910
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafce81f48184aa100eb3af78467ce82ab641fd55d10e43c48b302cd8897c128
+size 63516712
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I.json b/FR_RESULTS/FR.txt_100_4_0.002__I.json
new file mode 100644
index 0000000000000000000000000000000000000000..31f81e2cd37095c17a0248e4a5c3a2c6c8e33e0f
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6bc63f44c57e472ccf9918ee85113c5cde01c13e40be78f60f07a971150956
+size 357
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I_C.csv b/FR_RESULTS/FR.txt_100_4_0.002__I_C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..92710c74f71b50b1ec394fb840ad38009531db2e
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I_C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635b80c60907a1b5c26219b72ba2fc9834c8d0b9365d608607863482384cc997
+size 21417
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I_C.h5 b/FR_RESULTS/FR.txt_100_4_0.002__I_C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..fa31c37488cdab78bed0b7cf1ed39d249619b1f8
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I_C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60db91f829f0343fdfde0c6c1754b741a7f9e3e2251b93b837d440571ef79a3
+size 85963816
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I_C.json b/FR_RESULTS/FR.txt_100_4_0.002__I_C.json
new file mode 100644
index 0000000000000000000000000000000000000000..99964da76aad093156bf8565f73d0c759835f107
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I_C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc79654dc40611e7ca111bb15045f8e6fbe7f595a73a500f6ef319e65d93decc
+size 364
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I_C_index b/FR_RESULTS/FR.txt_100_4_0.002__I_C_index
new file mode 100644
index 0000000000000000000000000000000000000000..c5297f4a6e4811c2eb25f405d9d2574226ec0c57
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I_C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32f1d51c54457712159ebb9e6f9e985e61f3f4236521ec9d990d0b24fdb13a5
+size 1060266
diff --git a/FR_RESULTS/FR.txt_100_4_0.002__I_index b/FR_RESULTS/FR.txt_100_4_0.002__I_index
new file mode 100644
index 0000000000000000000000000000000000000000..368383589d1565b9af63d48ff8de24df0b4fc22e
--- /dev/null
+++ b/FR_RESULTS/FR.txt_100_4_0.002__I_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39af04607deba9535c5c8db22f8f29575cd8864c1b05f3ae6179132e97366fe6
+size 706706
diff --git a/LogDisplay.ipynb b/LogDisplay.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..7009ee6e01ba35ef5db751dfa75bd23b343200ef
--- /dev/null
+++ b/LogDisplay.ipynb
@@ -0,0 +1,561 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from glob import glob\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from ipywidgets import interact, interactive, fixed, interact_manual\n",
+    "import ipywidgets as widgets\n",
+    "from glob import glob\n",
+    "\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib as mpl\n",
+    "sns.set(style=\"whitegrid\")\n",
+    "sns.set_context('paper')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_dir = \"FR_RESULTS/\" # CHANGE TO \"TEXAS_IDF_RESULTS\" to plot the results obtained on the \"Ile de France + Texas\" dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DATASET = \"FRANCE\" # Change dataset name to IDF_TEXAS if base_dir = \"TEXAS_IDF_RESULTS\"\n",
+    "fns = glob(base_dir + \"/*.json\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'dataset_name': 'FR.txt',\n",
+       " 'rel_code': 'A',\n",
+       " 'cooc_sample_size': 3,\n",
+       " 'adj_iteration': 1,\n",
+       " 'ngram_size': 4,\n",
+       " 'tolerance_value': 0.002,\n",
+       " 'epochs': 100,\n",
+       " 'embedding_dim': 256,\n",
+       " 'word2vec_iter_nb': 50,\n",
+       " 'index_fn': 'outputs/FR.txt_100_4_0.002__A_index',\n",
+       " 'keras_model_fn': 'outputs/FR.txt_100_4_0.002__A.h5',\n",
+       " 'train_test_history_fn': 'outputs/FR.txt_100_4_0.002__A.csv'}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "json.load(open(fns[0]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def decode_fn(filename):\n",
+    "    \"\"\"\n",
+    "    Extract data and metadata from an output log file\n",
+    "    \"\"\"\n",
+    "    data = json.load(open(filename))\n",
+    "    return {\n",
+    "        \"dataset\":data[\"dataset_name\"],\n",
+    "        \"epochs\":data[\"epochs\"],\n",
+    "        \"ngram size\":data[\"ngram_size\"],\n",
+    "        \"k\":data[\"tolerance_value\"],\n",
+    "        \"tuple\" : data[\"rel_code\"],\n",
+    "        \"data\":pd.read_csv(base_dir + data[\"train_test_history_fn\"].split(\"/\")[-1],index_col=0)\n",
+    "    }\n",
+    "\n",
+    "def plot(fig,ax,data,keys,test=False):\n",
+    "    \"\"\"\n",
+    "    Generate a plot from an output log \n",
+    "    \"\"\"\n",
+    "    for k in keys:\n",
+    "        new_k = k\n",
+    "        label = \"{0}-N{1} (Train)\".format(\"LSTM\",data[\"ngram size\"])\n",
+    "        data[\"data\"][new_k].plot(label=label,legend=True,ax=ax)#+\" Train\",legend=True)#,color=color[k],ax=ax)\n",
+    "        if test:\n",
+    "            new_k=\"val_\"+new_k\n",
+    "        label = \"{0}-N{1} (Test)\".format(\"LSTM\",data[\"ngram size\"])\n",
+    "        data[\"data\"][new_k].plot(label=label,legend=True,ax=ax,linestyle='--')#+\" Train\",legend=True)#,color=color[k],ax=ax)\n",
+    "    \n",
+    "    ax.legend(bbox_to_anchor=(1.04,1), prop={'size': 15})\n",
+    "    ax.set_ylim((0,1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4ab08eff02444216aefe8633fa798c99",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "interactive(children=(Dropdown(description='K-value:', index=1, options=(0.001, 0.002), value=0.002), Dropdown…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<function __main__.foo(kvalue, spatrel)>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kvalue = widgets.Dropdown(\n",
+    "    options=[0.001,0.002],\n",
+    "    value=0.002,\n",
+    "    description='K-value:',\n",
+    "    disabled=False,\n",
+    ")\n",
+    "spatrel = widgets.Dropdown(\n",
+    "    options=[\"I\",\"A\",\"AI\",\"AIC\",\"AC\",\"IC\",\"C\"],\n",
+    "    value=\"I\",\n",
+    "    description='Spatial Relation Used:',\n",
+    "    disabled=False,\n",
+    ")\n",
+    "\n",
+    "def foo(kvalue,spatrel):\n",
+    "    keys=[\"Output_LON_accuracy_at_k_lon\"]#,\"Output_LAT_accuracy_at_k\"]\n",
+    "    fig, (ax,ax2) = plt.subplots(2,figsize=(10,10))\n",
+    "    for fn in fns:\n",
+    "        data = decode_fn(fn)\n",
+    "        if data[\"tuple\"] == spatrel and data[\"k\"] == kvalue:\n",
+    "            plot(fig,ax,data,keys,test=True)\n",
+    "        \n",
+    "    ax.set_title(\"Longitude\")\n",
+    "    keys=[\"Output_LAT_accuracy_at_k_lat\"]\n",
+    "    for fn in fns:\n",
+    "        data = decode_fn(fn)\n",
+    "        if data[\"tuple\"] == spatrel and data[\"k\"] == kvalue:\n",
+    "            plot(fig,ax2,data,keys,test=True)\n",
+    "    ax2.set_title(\"Latitude\")\n",
+    "    fig.suptitle(\"LSTM - accuracy@100km - 4-grams - Relation used {0}\".format(spatrel),y=0.95,weight=\"bold\")\n",
+    "    #plt.savefig(\"{2}_LSTM_{0}_{1}.png\".format(kvalue,spatrel,DATASET),bbox_inches = 'tight')\n",
+    "\n",
+    "interact(foo,kvalue=kvalue,spatrel=spatrel)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = decode_fn(fns[0])\n",
+    "df = data[\"data\"]\n",
+    "df[\"Relation(s) Used\"] = data[\"tuple\"]\n",
+    "df[\"epochs\"] = np.arange(100)\n",
+    "for fn in fns[1:]:\n",
+    "    data = decode_fn(fn)\n",
+    "    new_df = data[\"data\"]\n",
+    "    new_df[\"epochs\"] = np.arange(100)\n",
+    "    new_df[\"Relation(s) Used\"] = data[\"tuple\"]\n",
+    "    df = pd.concat((df,new_df))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>val_loss</th>\n",
+       "      <th>val_Output_LON_loss</th>\n",
+       "      <th>val_Output_LAT_loss</th>\n",
+       "      <th>val_Output_LON_accuracy_at_k_lon</th>\n",
+       "      <th>val_Output_LAT_accuracy_at_k_lat</th>\n",
+       "      <th>loss</th>\n",
+       "      <th>Output_LON_loss</th>\n",
+       "      <th>Output_LAT_loss</th>\n",
+       "      <th>Output_LON_accuracy_at_k_lon</th>\n",
+       "      <th>Output_LAT_accuracy_at_k_lat</th>\n",
+       "      <th>Relation(s) Used</th>\n",
+       "      <th>epochs</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.000115</td>\n",
+       "      <td>0.000045</td>\n",
+       "      <td>0.000070</td>\n",
+       "      <td>0.295377</td>\n",
+       "      <td>0.509287</td>\n",
+       "      <td>0.000381</td>\n",
+       "      <td>0.000188</td>\n",
+       "      <td>0.000193</td>\n",
+       "      <td>0.273675</td>\n",
+       "      <td>0.425386</td>\n",
+       "      <td>A</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>72</th>\n",
+       "      <td>0.000058</td>\n",
+       "      <td>0.000022</td>\n",
+       "      <td>0.000036</td>\n",
+       "      <td>0.584888</td>\n",
+       "      <td>0.779450</td>\n",
+       "      <td>0.000004</td>\n",
+       "      <td>0.000002</td>\n",
+       "      <td>0.000003</td>\n",
+       "      <td>0.957315</td>\n",
+       "      <td>0.995521</td>\n",
+       "      <td>A</td>\n",
+       "      <td>72</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>71</th>\n",
+       "      <td>0.000058</td>\n",
+       "      <td>0.000022</td>\n",
+       "      <td>0.000036</td>\n",
+       "      <td>0.587047</td>\n",
+       "      <td>0.775844</td>\n",
+       "      <td>0.000004</td>\n",
+       "      <td>0.000002</td>\n",
+       "      <td>0.000003</td>\n",
+       "      <td>0.954727</td>\n",
+       "      <td>0.995618</td>\n",
+       "      <td>A</td>\n",
+       "      <td>71</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>70</th>\n",
+       "      <td>0.000056</td>\n",
+       "      <td>0.000022</td>\n",
+       "      <td>0.000034</td>\n",
+       "      <td>0.591935</td>\n",
+       "      <td>0.784623</td>\n",
+       "      <td>0.000005</td>\n",
+       "      <td>0.000002</td>\n",
+       "      <td>0.000003</td>\n",
+       "      <td>0.953021</td>\n",
+       "      <td>0.994972</td>\n",
+       "      <td>A</td>\n",
+       "      <td>70</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>69</th>\n",
+       "      <td>0.000058</td>\n",
+       "      <td>0.000022</td>\n",
+       "      <td>0.000036</td>\n",
+       "      <td>0.586314</td>\n",
+       "      <td>0.775825</td>\n",
+       "      <td>0.000005</td>\n",
+       "      <td>0.000002</td>\n",
+       "      <td>0.000003</td>\n",
+       "      <td>0.950501</td>\n",
+       "      <td>0.994548</td>\n",
+       "      <td>A</td>\n",
+       "      <td>69</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>0.000084</td>\n",
+       "      <td>0.000030</td>\n",
+       "      <td>0.000054</td>\n",
+       "      <td>0.699088</td>\n",
+       "      <td>0.819236</td>\n",
+       "      <td>0.000030</td>\n",
+       "      <td>0.000013</td>\n",
+       "      <td>0.000018</td>\n",
+       "      <td>0.726226</td>\n",
+       "      <td>0.883270</td>\n",
+       "      <td>IC</td>\n",
+       "      <td>27</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>0.000084</td>\n",
+       "      <td>0.000032</td>\n",
+       "      <td>0.000051</td>\n",
+       "      <td>0.696359</td>\n",
+       "      <td>0.823050</td>\n",
+       "      <td>0.000034</td>\n",
+       "      <td>0.000014</td>\n",
+       "      <td>0.000021</td>\n",
+       "      <td>0.709992</td>\n",
+       "      <td>0.865662</td>\n",
+       "      <td>IC</td>\n",
+       "      <td>26</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>0.000084</td>\n",
+       "      <td>0.000027</td>\n",
+       "      <td>0.000057</td>\n",
+       "      <td>0.673946</td>\n",
+       "      <td>0.816693</td>\n",
+       "      <td>0.000032</td>\n",
+       "      <td>0.000013</td>\n",
+       "      <td>0.000019</td>\n",
+       "      <td>0.718581</td>\n",
+       "      <td>0.875147</td>\n",
+       "      <td>IC</td>\n",
+       "      <td>24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35</th>\n",
+       "      <td>0.000090</td>\n",
+       "      <td>0.000032</td>\n",
+       "      <td>0.000058</td>\n",
+       "      <td>0.713059</td>\n",
+       "      <td>0.829505</td>\n",
+       "      <td>0.000024</td>\n",
+       "      <td>0.000010</td>\n",
+       "      <td>0.000014</td>\n",
+       "      <td>0.760739</td>\n",
+       "      <td>0.911580</td>\n",
+       "      <td>IC</td>\n",
+       "      <td>35</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>99</th>\n",
+       "      <td>0.000096</td>\n",
+       "      <td>0.000031</td>\n",
+       "      <td>0.000065</td>\n",
+       "      <td>0.740629</td>\n",
+       "      <td>0.841372</td>\n",
+       "      <td>0.000010</td>\n",
+       "      <td>0.000005</td>\n",
+       "      <td>0.000006</td>\n",
+       "      <td>0.872880</td>\n",
+       "      <td>0.972612</td>\n",
+       "      <td>IC</td>\n",
+       "      <td>99</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>700 rows × 12 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    val_loss  val_Output_LON_loss  val_Output_LAT_loss  \\\n",
+       "0   0.000115             0.000045             0.000070   \n",
+       "72  0.000058             0.000022             0.000036   \n",
+       "71  0.000058             0.000022             0.000036   \n",
+       "70  0.000056             0.000022             0.000034   \n",
+       "69  0.000058             0.000022             0.000036   \n",
+       "..       ...                  ...                  ...   \n",
+       "27  0.000084             0.000030             0.000054   \n",
+       "26  0.000084             0.000032             0.000051   \n",
+       "24  0.000084             0.000027             0.000057   \n",
+       "35  0.000090             0.000032             0.000058   \n",
+       "99  0.000096             0.000031             0.000065   \n",
+       "\n",
+       "    val_Output_LON_accuracy_at_k_lon  val_Output_LAT_accuracy_at_k_lat  \\\n",
+       "0                           0.295377                          0.509287   \n",
+       "72                          0.584888                          0.779450   \n",
+       "71                          0.587047                          0.775844   \n",
+       "70                          0.591935                          0.784623   \n",
+       "69                          0.586314                          0.775825   \n",
+       "..                               ...                               ...   \n",
+       "27                          0.699088                          0.819236   \n",
+       "26                          0.696359                          0.823050   \n",
+       "24                          0.673946                          0.816693   \n",
+       "35                          0.713059                          0.829505   \n",
+       "99                          0.740629                          0.841372   \n",
+       "\n",
+       "        loss  Output_LON_loss  Output_LAT_loss  Output_LON_accuracy_at_k_lon  \\\n",
+       "0   0.000381         0.000188         0.000193                      0.273675   \n",
+       "72  0.000004         0.000002         0.000003                      0.957315   \n",
+       "71  0.000004         0.000002         0.000003                      0.954727   \n",
+       "70  0.000005         0.000002         0.000003                      0.953021   \n",
+       "69  0.000005         0.000002         0.000003                      0.950501   \n",
+       "..       ...              ...              ...                           ...   \n",
+       "27  0.000030         0.000013         0.000018                      0.726226   \n",
+       "26  0.000034         0.000014         0.000021                      0.709992   \n",
+       "24  0.000032         0.000013         0.000019                      0.718581   \n",
+       "35  0.000024         0.000010         0.000014                      0.760739   \n",
+       "99  0.000010         0.000005         0.000006                      0.872880   \n",
+       "\n",
+       "    Output_LAT_accuracy_at_k_lat Relation(s) Used  epochs  \n",
+       "0                       0.425386                A       0  \n",
+       "72                      0.995521                A      72  \n",
+       "71                      0.995618                A      71  \n",
+       "70                      0.994972                A      70  \n",
+       "69                      0.994548                A      69  \n",
+       "..                           ...              ...     ...  \n",
+       "27                      0.883270               IC      27  \n",
+       "26                      0.865662               IC      26  \n",
+       "24                      0.875147               IC      24  \n",
+       "35                      0.911580               IC      35  \n",
+       "99                      0.972612               IC      99  \n",
+       "\n",
+       "[700 rows x 12 columns]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sort_values(by=\"Relation(s) Used\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df[df.epochs.isin(list(range(0,100,5)))]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[None, None]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1051.71x432 with 7 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "g = sns.FacetGrid(df, col=\"Relation(s) Used\", col_wrap=4, height=3, ylim=(0, 1),xlim=(0,100))\n",
+    "\n",
+    "g.map(sns.lineplot,\"epochs\", \"Output_LON_accuracy_at_k_lon\", color=\"#e74c3c\", ci=None,label=\"Longitude Train accuracy\",marker=\"o\",markersize=7);\n",
+    "g.map(sns.lineplot,\"epochs\", \"val_Output_LON_accuracy_at_k_lon\", color=\"#e74c3c\", ci=None,label=\"Longitude Test accuracy\",marker=\"^\",markersize=7);\n",
+    "\n",
+    "g.map(sns.lineplot,\"epochs\", \"Output_LAT_accuracy_at_k_lat\", color=\"#2980b9\", ci=None,label=\"Latitude Train accuracy\",marker=\"o\",markersize=7);\n",
+    "g.map(sns.lineplot,\"epochs\", \"val_Output_LAT_accuracy_at_k_lat\", color=\"#2980b9\", ci=None,label=\"Latitude Test accuracy\",marker=\"^\",markersize=7);\n",
+    "g.set(xlabel='Epochs', ylabel='Accuracy@100km')\n",
+    "g.set(xticks=np.arange(0,100,10))\n",
+    "g.add_legend(bbox_to_anchor=(0.80, 0.20),fontsize=\"large\",title=\"Legend\",title_fontsize=\"40\",frameon=True)\n",
+    "#g.fig.suptitle('Longitude Prediction (Accuracy@100km)',position=(0.58,.09),fontsize=15)\n",
+    "g.fig.subplots_adjust(top=.9)\n",
+    "plt.setp(g._legend.get_title(), fontsize=15)\n",
+    "#plt.savefig(\"{0}_100km.pdf\".format(DATASET),bbox_inches = 'tight')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.csv b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.csv
new file mode 100644
index 0000000000000000000000000000000000000000..9a42305bcaec10672311842a0d1e8dd334307d0c
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4cea6170cc219234e0e62e6d79eceef42bf556a0cf7b023489310775da81b0
+size 21521
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.h5 b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.h5
new file mode 100644
index 0000000000000000000000000000000000000000..2caa78a20efb8a3eac123d04c02c9c92edf82ad3
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50481c3d30b67bda917520184c63d6c895ec74442c19731f561b3a6833e9f34f
+size 40501288
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.json b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.json
new file mode 100644
index 0000000000000000000000000000000000000000..bf4c9d76f0def468b8d3d7604451f0ac8f16fed7
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294aab854c42ffa9f0a7b79704f7730147e1c9c20bc58519187c908cf44325ab
+size 368
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.csv b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..b174a0655511c086a2f8119a7b10c7a140387099
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cabac0ca054bf66f1fb55a209e3a23e840d6eacb8e5ac670f0132143d310b363
+size 21412
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.h5 b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..2b655d5cd7134e79ee8c7af349ccb79d470e2508
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9b8daefb56ac6d2ac999a3eb721d747c25b09d054707b95373fb14997c0ad9
+size 64724008
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.json b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.json
new file mode 100644
index 0000000000000000000000000000000000000000..cb9eeca679275dd0a1749c71180880128ccae7c4
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84dc3deb1c1c81442cfe960c3bb636670d5da792b8180d676873a2ab3c2239d
+size 375
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C_index b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C_index
new file mode 100644
index 0000000000000000000000000000000000000000..ae45bf00f562dff8ae482c9b0555fa7216ac1dd5
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed723508e73164924657ea5b55970382f0ae88dddd1fbd3fff351f8b11321db
+size 706021
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.csv b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.csv
new file mode 100644
index 0000000000000000000000000000000000000000..b7baa48f7b6bc15a3249eaa1f3994f9d6fcd0c2b
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4263b2b5b845c7883749eba9c39a3841cdd2382fca279a8cc69b280c225ceb05
+size 21462
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.h5 b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.h5
new file mode 100644
index 0000000000000000000000000000000000000000..4c4e359dd6652d2f97658fc9fa042ecb1fd29cda
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd60f4e3e57c76ac819a82842090eb9f252fbf4424eec009c01595b132c6979
+size 40501288
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.json b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.json
new file mode 100644
index 0000000000000000000000000000000000000000..1f9bcfbf8f1cf7b8d106662dd31212c0778af113
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03f76c46da4fe93f81ad9631e5d893047bd4b7d7832e9af946c8163a7a5b6fe
+size 375
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.csv b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..e6c27bfd422b7b1e749149202f6d5a3984f3f0bd
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cdb4bd2bbbf8a4cd65f34995d3e225667af6a48b4f2abccc340172f0cc28d9
+size 21433
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.h5 b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..598336804ad8ff1fefde0853f75fbac23b51f503
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5bd2048ac19fd0a11cc9fb6d4e63a9f2da2a8f48fd6bf63f0f63d5160ae759
+size 64724008
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.json b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.json
new file mode 100644
index 0000000000000000000000000000000000000000..b6d6fa0ee1dc7bf413f467f369e84dad9f6e6fdc
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8076042b7f7b9bac440301108acc1ccfaa0d7ceea9e4ae1d64c5e932bd4b17d2
+size 382
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C_index b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C_index
new file mode 100644
index 0000000000000000000000000000000000000000..ae45bf00f562dff8ae482c9b0555fa7216ac1dd5
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed723508e73164924657ea5b55970382f0ae88dddd1fbd3fff351f8b11321db
+size 706021
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_index b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_index
new file mode 100644
index 0000000000000000000000000000000000000000..43b86de78087d597d5b9b44e5836fc47c17ec110
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_I_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246035224bab4ed59c0c57cc432fa8b9674a8985ca9db998d4e2dc32bb06325f
+size 330286
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_index b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_index
new file mode 100644
index 0000000000000000000000000000000000000000..43b86de78087d597d5b9b44e5836fc47c17ec110
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__A_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246035224bab4ed59c0c57cc432fa8b9674a8985ca9db998d4e2dc32bb06325f
+size 330286
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.csv b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..5be8629a35743dc5abd3ea9d3bc8b50c3727b008
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bebfb95b24e81707d928eb544cf015daeeac0b3f2e525ffde7965cb633f907a
+size 21439
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.h5 b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..4070360b8c9836d27887d7d73c8962a6acf7acdf
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc349d43e4486df2a120e902296845dbb0e8669f0b424b5f0e1c02768b3078e
+size 64724008
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.json b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.json
new file mode 100644
index 0000000000000000000000000000000000000000..4765e1d288c00e5180cde65df0276503058e4e18
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d4cb519a8673e8943d60411a57bc2e1e2eb158f41688457b1601eb497bfc51
+size 368
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C_index b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C_index
new file mode 100644
index 0000000000000000000000000000000000000000..ae45bf00f562dff8ae482c9b0555fa7216ac1dd5
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed723508e73164924657ea5b55970382f0ae88dddd1fbd3fff351f8b11321db
+size 706021
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.csv b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.csv
new file mode 100644
index 0000000000000000000000000000000000000000..ee60cf14448d7cf405171867803aab41caad8029
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777ecc4d7f165a948bac650b8e31ea8bf11a093363f7003e4d964436088157ca
+size 21446
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.h5 b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.h5
new file mode 100644
index 0000000000000000000000000000000000000000..434a22927ea97ca7a167af0823c02dac8f198cb3
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b5f889a731274fbab6ece2f9a88ec4c9b68eb3725b19caabf7e9fad8ab9627
+size 40504032
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.json b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.json
new file mode 100644
index 0000000000000000000000000000000000000000..2584b94a6115816c67f8cc9ecbb7568221699549
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9125963c16e35eaa5bc1d7b8ce998b5409f772f97217cd09ac5893ca5aeadcbe
+size 368
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.csv b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.csv
new file mode 100644
index 0000000000000000000000000000000000000000..3cdfd1994afe1715fa92093181f2e0ac4bd339d2
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3f0d55001e84bf80f3140c9c422a5a9037dcc2bf7f26baaea9b51f5c8de9d3
+size 21433
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.h5 b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.h5
new file mode 100644
index 0000000000000000000000000000000000000000..3de655a1eb1077921b59052d9ec87f7cf8705b9e
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f69da5da9b139101175cb68a7032ac2ddb536c2e7dd2256e3fb0eecce973a9f
+size 64724008
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.json b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.json
new file mode 100644
index 0000000000000000000000000000000000000000..4c6941328f776c7d96ef69642c1dc24faaddd83e
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ad6db54a2ca8f7c666c41db75437801dc73572611822a316400a0683b81795
+size 375
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C_index b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C_index
new file mode 100644
index 0000000000000000000000000000000000000000..ae45bf00f562dff8ae482c9b0555fa7216ac1dd5
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_C_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed723508e73164924657ea5b55970382f0ae88dddd1fbd3fff351f8b11321db
+size 706021
diff --git a/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_index b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_index
new file mode 100644
index 0000000000000000000000000000000000000000..43b86de78087d597d5b9b44e5836fc47c17ec110
--- /dev/null
+++ b/TEXAS_IDF_RESULTS/US_FR.txt_100_4_0.002__I_index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246035224bab4ed59c0c57cc432fa8b9674a8985ca9db998d4e2dc32bb06325f
+size 330286
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..70a0ba73f3a01fc482b5acaeb7d33ab63bd56a4e
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,5 @@
+ipywidgets
+pandas
+numpy
+seaborn
+matplotlib