Skip to content

Commit

Permalink
cleaned up activity counts notebook
Browse files Browse the repository at this point in the history
  • Loading branch information
@michaelaye
michaelaye committed Feb 5, 2016
1 parent 3867da3 commit 7b9ac2a
Show file tree
Hide file tree
Showing 2 changed files with 68 additions and 246 deletions.
197 changes: 38 additions & 159 deletions notebooks/2015-10-26 Activity counts.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@
" # writing in dictionary here b/c later I convert it to pd.DataFrame\n",
" # for which a dictionary is a natural input format\n",
" d = {}\n",
" d['image_name'] = img_name\n",
" d['obsid'] = img_name\n",
" blotch_fname = root / '{}_blotches_latlons.csv'.format(img_name)\n",
" d['n_blotches'] = len(pd.read_csv(str(blotch_fname)))\n",
" fan_fname = root / '{}_fans_latlons.csv'.format(img_name)\n",
Expand Down Expand Up @@ -113,18 +113,7 @@
},
"outputs": [],
"source": [
"results = []\n",
"from IPython.display import display\n",
"from ipywidgets import IntProgress\n",
"t = IntProgress(min=0, max=len(region_data.Inca.season2)-1)\n",
"display(t)\n",
"for i, img_name in enumerate(region_data.Inca.season2):\n",
" t.value = i\n",
" try:\n",
" results.append(get_final_markings_counts(img_name))\n",
" except OSError:\n",
" continue\n",
"season2 = pd.DataFrame(results).sort_values(by='image_name')"
"from nbtools import ListProgressBar"
]
},
{
Expand All @@ -136,51 +125,14 @@
"outputs": [],
"source": [
"results = []\n",
"from IPython.display import display\n",
"from ipywidgets import IntProgress\n",
"t = IntProgress(min=0, max=len(region_data.Inca.season3)-1)\n",
"display(t)\n",
"for i, img_name in enumerate(region_data.Inca.season3):\n",
" t.value = i\n",
"progbar = ListProgressBar(region_data.Inca.season2)\n",
"for img_name in region_data.Inca.season2:\n",
" progbar.value = img_name\n",
" try:\n",
" results.append(get_final_markings_counts(img_name))\n",
" except OSError:\n",
" continue\n",
"season3 = pd.DataFrame(results).sort_values(by='image_name')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [],
"source": [
"season2.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"metadata = pd.read_csv(io.analysis_folder() / \"P4_10-18-15_H_lat_lng.csv\")"
"season2 = pd.DataFrame(results).sort_values(by='obsid')"
]
},
{
Expand All @@ -191,32 +143,27 @@
},
"outputs": [],
"source": [
"metadata"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from hirise.hirise_tools import get_rdr_label, labels_root"
"results = []\n",
"progbar = ListProgressBar(region_data.Inca.season3)\n",
"for img_name in region_data.Inca.season3:\n",
" progbar.value = img_name\n",
" try:\n",
" results.append(get_final_markings_counts(img_name))\n",
" except OSError:\n",
" continue\n",
"season3 = pd.DataFrame(results).sort_values(by='obsid')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
"collapsed": false,
"scrolled": true
},
"outputs": [],
"source": [
"import pvl\n",
"def get_nlines_from_label(labelfname):\n",
" module = pvl.load(str(labelfname))\n",
" return module['UNCOMPRESSED_FILE']['IMAGE']['LINE_SAMPLES']"
"season2.head()"
]
},
{
Expand All @@ -227,18 +174,7 @@
},
"outputs": [],
"source": [
"p = labels_root()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"metadata['labelpath'] = metadata.HiRISE_image.map(lambda x: p / (x + '_RED.LBL'))"
"season2.head()"
]
},
{
Expand All @@ -249,18 +185,10 @@
},
"outputs": [],
"source": [
"metadata['nsamples'] = metadata.labelpath.map(get_nlines_from_label)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"metadata.set_index('HiRISE_image', inplace=True)"
"season2_meta = pd.read_csv(io.analysis_folder() / 'inca_season2_metadata.csv')\n",
"# dropping the label path here as it's not required\n",
"# if it is, delete this line.\n",
"season2_meta.drop('path', axis=1, inplace=True)"
]
},
{
Expand All @@ -271,8 +199,7 @@
},
"outputs": [],
"source": [
"season2.set_index('image_name', inplace=True)\n",
"season3.set_index('image_name', inplace=True)"
"season2_meta.head()"
]
},
{
Expand All @@ -283,7 +210,7 @@
},
"outputs": [],
"source": [
"season2 = season2.join(metadata['solar_longitude binning nsamples'.split()])"
"season2 = season2.merge(season2_meta, on='obsid')"
]
},
{
Expand All @@ -294,7 +221,7 @@
},
"outputs": [],
"source": [
"season3 = season3.join(metadata['solar_longitude binning nsamples'.split()])"
"season2.head()"
]
},
{
Expand All @@ -305,7 +232,8 @@
},
"outputs": [],
"source": [
"season2.set_index('solar_longitude', inplace=True)"
"path = io.analysis_folder() / 'inca_season3_metadata.csv'\n",
"season3_meta = pd.read_csv(path)"
]
},
{
Expand All @@ -316,7 +244,7 @@
},
"outputs": [],
"source": [
"season3.set_index('solar_longitude', inplace=True)"
"season3 = season3.merge(season3_meta, on='obsid')"
]
},
{
Expand All @@ -327,7 +255,9 @@
},
"outputs": [],
"source": [
"season2['both'] = season2.n_blotches + season2.n_fans"
"season2.set_index('l_s', inplace=True)\n",
"\n",
"season3.set_index('l_s', inplace=True)"
]
},
{
Expand All @@ -338,6 +268,8 @@
},
"outputs": [],
"source": [
"season2['both'] = season2.n_blotches + season2.n_fans\n",
"\n",
"season3['both'] = season3.n_blotches + season3.n_fans"
]
},
Expand All @@ -349,18 +281,9 @@
},
"outputs": [],
"source": [
"season2['scaled'] = season2.both / season2.nsamples / season2.binning"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"season3['scaled'] = season3.both / season3.nsamples / season3.binning"
"season2['scaled'] = season2.both / season2.line_samples / season2.binning\n",
"\n",
"season3['scaled'] = season3.both / season3.line_samples / season3.binning"
]
},
{
Expand All @@ -371,9 +294,7 @@
},
"outputs": [],
"source": [
"%matplotlib notebook\n",
"import seaborn as sns\n",
"sns.set()"
"%matplotlib notebook"
]
},
{
Expand All @@ -393,48 +314,6 @@
"plt.title(\"Number of markings in Inca City region,scaled for binning and image size.\")\n",
"plt.savefig('/Users/klay6683/Desktop/inca_s23.pdf')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"season2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"season3"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"season3.scaled.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
Expand Down
Loading

0 comments on commit 7b9ac2a

Please sign in to comment.