Skip to content

GitLab

Commit 31c6b611 authored by Unknown's avatar Unknown
Browse files

Updated the tutorial to also show the PycroDataset object.

parent 9c11a8f1
Expand all Hide whitespace changes
Inline Side-by-side
docs/_autosummary/backreferences/pycroscopy.PycroDataset.examples 0 → 100644
View file @ 31c6b611
Examples using ``pycroscopy.PycroDataset``
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. raw:: html
<div class="sphx-glr-thumbcontainer" tooltip="**Suhas Somnath** 8/8/2017">
.. only:: html
.. figure:: /auto_examples/images/thumb/sphx_glr_tutorial_03_multidimensional_data_thumb.png
:ref:`sphx_glr_auto_examples_tutorial_03_multidimensional_data.py`
.. raw:: html
</div>
.. only:: not html
* :ref:`sphx_glr_auto_examples_tutorial_03_multidimensional_data.py`
docs/auto_examples/load_dataset_example.ipynb
View file @ 31c6b611
{
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"name": "python3",
"language": "python"
},
"language_info": {
"codemirror_mode": {
"version": 3,
"name": "ipython"
},
"mimetype": "text/x-python",
"name": "python",
"file_extension": ".py",
"version": "3.5.2",
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python"
}
},
"cells": [
{
"metadata": {
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"%matplotlib inline"
]
......@@ -23,32 +42,13 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"# Code source: pycroscopy\n# Liscense: MIT\n\nfrom __future__ import division, print_function, absolute_import, unicode_literals\nimport h5py\ntry:\n # This package is not part of anaconda and may need to be installed.\n import wget\nexcept ImportError:\n import pip\n pip.main(['install', 'wget'])\n import wget\n\nfrom os import remove\nimport pycroscopy as px\n\n# Downloading the file from the pycroscopy Github project\nurl = 'https://raw.githubusercontent.com/pycroscopy/pycroscopy/master/data/BELine_0004.h5'\nh5_path = 'temp.h5'\n_ = wget.download(url, h5_path)\n\n# h5_path = px.io_utils.uiGetFile(caption='Select .h5 file', filter='HDF5 file (*.h5)')\n\n# Read the file using using h5py:\nh5_file1 = h5py.File(h5_path, 'r')\n\n# Look at the contents of the file:\npx.hdf_utils.print_tree(h5_file1)\n\n# Access the \"Raw_Data\" dataset from its absolute path\nh5_raw1 = h5_file1['Measurement_000/Channel_000/Raw_Data']\nprint('h5_raw1: ', h5_raw1)\n\n# We can get to the same dataset through relative paths:\n\n# Access the Measurement_000 group first\nh5_meas_grp = h5_file1['Measurement_000']\nprint('h5_meas_grp:', h5_meas_grp)\n\n# Now we can access the \"Channel_000\" group via the h5_meas_grp object\nh5_chan_grp = h5_meas_grp['Channel_000']\n\n# And finally, the same raw dataset can be accessed as:\nh5_raw1_alias_1 = h5_chan_grp['Raw_Data']\nprint('h5_raw1_alias_1:', h5_raw1_alias_1)\n\n# Another way to get this dataset is via functions written in pycroscopy:\nh5_dsets = px.hdf_utils.getDataSet(h5_file1, 'Raw_Data')\nprint('h5_dsets:', h5_dsets)\n\n# In this case, there is only a single Raw_Data, so we an access it simply as:\nh5_raw1_alias_2 = h5_dsets[0]\nprint('h5_raw1_alias_2:', h5_raw1_alias_2)\n\n# Let's just check to see if these are indeed aliases of the same dataset:\nprint('All aliases of the same dataset?', h5_raw1 == h5_raw1_alias_1 and h5_raw1 == h5_raw1_alias_2)\n\n# Let's close this file\nh5_file1.close()\n\n# Load the dataset with pycroscopy\nhdf = px.ioHDF5(h5_path)\n\n# Getting the same h5py handle to the file:\nh5_file2 = hdf.file\n\nh5_raw2 = h5_file2['Measurement_000/Channel_000/Raw_Data']\nprint('h5_raw2:', h5_raw2)\n\nh5_file2.close()\n\n# Delete the temporarily downloaded h5 file:\nremove(h5_path)"
]
}
],
"nbformat_minor": 0,
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"name": "python3",
"language": "python"
},
"language_info": {
"mimetype": "text/x-python",
"nbconvert_exporter": "python",
"file_extension": ".py",
"pygments_lexer": "ipython3",
"version": "3.5.2",
"codemirror_mode": {
"version": 3,
"name": "ipython"
},
"name": "python"
}
},
"nbformat": 4
"nbformat": 4,
"nbformat_minor": 0
}
\ No newline at end of file
docs/auto_examples/microdata_example.ipynb
View file @ 31c6b611
{
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"name": "python3",
"language": "python"
},
"language_info": {
"codemirror_mode": {
"version": 3,
"name": "ipython"
},
"mimetype": "text/x-python",
"name": "python",
"file_extension": ".py",
"version": "3.5.2",
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python"
}
},
"cells": [
{
"metadata": {
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"%matplotlib inline"
]
......@@ -23,8 +42,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"# Code source: Chris Smith -- cq6@ornl.gov\n# Liscense: MIT\n\nimport numpy as np\nimport pycroscopy as px"
]
......@@ -41,8 +60,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"# First create some data\ndata1 = np.random.rand(5, 7)"
]
......@@ -59,8 +78,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"ds_main = px.MicroDataset('Main_Data', data=data1, parent='/')"
]
......@@ -77,8 +96,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"ds_empty = px.MicroDataset('Empty_Data', data=[], dtype=np.float32, maxshape=[7, 5, 3])"
]
......@@ -95,8 +114,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"data_group = px.MicroDataGroup('Data_Group', parent='/')\n\nroot_group = px.MicroDataGroup('/')\n\n# After creating the group, we then add an existing object as its child.\ndata_group.addChildren([ds_empty])\nroot_group.addChildren([ds_main, data_group])"
]
......@@ -113,8 +132,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"root_group.showTree()"
]
......@@ -131,8 +150,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"# First we specify the path to the file\nh5_path = 'microdata_test.h5'\n\n# Then we use the ioHDF5 class to build the file from our objects.\nhdf = px.ioHDF5(h5_path)"
]
......@@ -149,8 +168,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"h5_refs = hdf.writeData(root_group, print_log=True)\n\n# We can use these references to get the h5py dataset and group objects\nh5_main = px.io.hdf_utils.getH5DsetRefs(['Main_Data'], h5_refs)[0]\nh5_empty = px.io.hdf_utils.getH5DsetRefs(['Empty_Data'], h5_refs)[0]"
]
......@@ -167,8 +186,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"print(np.allclose(h5_main[()], data1))"
]
......@@ -185,8 +204,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"data2 = np.random.rand(*h5_empty.shape)\nh5_empty[:] = data2[:]"
]
......@@ -203,8 +222,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"h5_file = hdf.file\nh5_file.flush()"
]
......@@ -221,32 +240,13 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"h5_file.close()"
]
}
],
"nbformat_minor": 0,
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"name": "python3",
"language": "python"
},
"language_info": {
"mimetype": "text/x-python",
"nbconvert_exporter": "python",
"file_extension": ".py",
"pygments_lexer": "ipython3",
"version": "3.5.2",
"codemirror_mode": {
"version": 3,
"name": "ipython"
},
"name": "python"
}
},
"nbformat": 4
"nbformat": 4,
"nbformat_minor": 0
}
\ No newline at end of file
docs/auto_examples/plot_spectral_unmixing.ipynb
View file @ 31c6b611
{
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"name": "python3",
"language": "python"
},
"language_info": {
"codemirror_mode": {
"version": 3,
"name": "ipython"
},
"mimetype": "text/x-python",
"name": "python",
"file_extension": ".py",
"version": "3.5.2",
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python"
}
},
"cells": [
{
"metadata": {
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"%matplotlib inline"
]
......@@ -23,8 +42,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"#Import packages\n\n# Ensure that this code works on both python 2 and python 3\nfrom __future__ import division, print_function, absolute_import, unicode_literals\n\n# basic numeric computation:\nimport numpy as np\n\n# The package used for creating and manipulating HDF5 files:\nimport h5py\n\n# Plotting and visualization:\nimport matplotlib.pyplot as plt\nfrom mpl_toolkits.axes_grid1 import make_axes_locatable\n\n# for downloading files:\nimport wget\nimport os\n\n# multivariate analysis:\nfrom sklearn.cluster import KMeans\nfrom sklearn.decomposition import NMF\nfrom pysptools import eea\nimport pysptools.abundance_maps as amp\nfrom pysptools.eea import nfindr\n\n# finally import pycroscopy:\nimport pycroscopy as px\n\n\"\"\"\n \n\"\"\""
]
......@@ -41,8 +60,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"data_file_path = 'temp_um.h5'\n# download the data file from Github:\nurl = 'https://raw.githubusercontent.com/pycroscopy/pycroscopy/master/data/BELine_0004.h5'\n_ = wget.download(url, data_file_path, bar=None)\n\nhdf = px.ioHDF5(data_file_path)\nh5_file = hdf.file\n\nprint('Contents of data file:')\nprint('----------------------')\npx.hdf_utils.print_tree(h5_file)\nprint('----------------------')\n\nh5_meas_grp = h5_file['Measurement_000']\n\n# Extracting some basic parameters:\nnum_rows = px.hdf_utils.get_attr(h5_meas_grp,'grid_num_rows')\nnum_cols = px.hdf_utils.get_attr(h5_meas_grp,'grid_num_cols')\n\n# Getting a reference to the main dataset:\nh5_main = h5_meas_grp['Channel_000/Raw_Data']\n\n# Extracting the X axis - vector of frequencies\nh5_spec_vals = px.hdf_utils.getAuxData(h5_main,'Spectroscopic_Values')[-1]\nfreq_vec = np.squeeze(h5_spec_vals.value) * 1E-3\n\nprint('Data currently of shape:', h5_main.shape)\n\nx_label = 'Frequency (kHz)'\ny_label = 'Amplitude (a.u.)'"
]
......@@ -59,8 +78,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"px.viz.be_viz_utils.jupyter_visualize_be_spectrograms(h5_main)"
]
......@@ -77,8 +96,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"h5_svd_group = px.doSVD(h5_main, num_comps=256)\n\nh5_u = h5_svd_group['U']\nh5_v = h5_svd_group['V']\nh5_s = h5_svd_group['S']\n\n# Since the two spatial dimensions (x, y) have been collapsed to one, we need to reshape the abundance maps:\nabun_maps = np.reshape(h5_u[:,:25], (num_rows, num_cols, -1))\n\n# Visualize the variance / statistical importance of each component:\npx.plot_utils.plotScree(h5_s, title='Note the exponential drop of variance with number of components')\n\n# Visualize the eigenvectors:\nfirst_evecs = h5_v[:9, :]\n\npx.plot_utils.plot_loops(freq_vec, np.abs(first_evecs), x_label=x_label, y_label=y_label, plots_on_side=3,\n subtitles='Component', title='SVD Eigenvectors (Amplitude)', evenly_spaced=False)\npx.plot_utils.plot_loops(freq_vec, np.angle(first_evecs), x_label=x_label, y_label='Phase (rad)', plots_on_side=3,\n subtitles='Component', title='SVD Eigenvectors (Phase)', evenly_spaced=False)\n\n# Visualize the abundance maps:\npx.plot_utils.plot_map_stack(abun_maps, num_comps=9, heading='SVD Abundance Maps',\n color_bar_mode='single', cmap='inferno')"
]
......@@ -95,8 +114,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"num_clusters = 4\n\nestimators = px.Cluster(h5_main, 'KMeans', n_clusters=num_clusters)\nh5_kmeans_grp = estimators.do_cluster(h5_main)\nh5_kmeans_labels = h5_kmeans_grp['Labels']\nh5_kmeans_mean_resp = h5_kmeans_grp['Mean_Response']\n\npx.plot_utils.plot_cluster_h5_group(h5_kmeans_grp)"
]
......@@ -113,8 +132,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"num_comps = 4\n\n# get the non-negative portion of the dataset\ndata_mat = np.abs(h5_main)\n\nmodel = NMF(n_components=num_comps, init='random', random_state=0)\nmodel.fit(data_mat)\n\nfig, axis = plt.subplots(figsize=(5.5, 5))\npx.plot_utils.plot_line_family(axis, freq_vec, model.components_, label_prefix='NMF Component #')\naxis.set_xlabel(x_label, fontsize=12)\naxis.set_ylabel(y_label, fontsize=12)\naxis.set_title('NMF Components', fontsize=14)\naxis.legend(bbox_to_anchor=[1.0, 1.0], fontsize=12)"
]
......@@ -131,8 +150,8 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"num_comps = 4\n\n# get the amplitude component of the dataset\ndata_mat = np.abs(h5_main)\n\nnfindr_results = eea.nfindr.NFINDR(data_mat, num_comps) #Find endmembers\nend_members = nfindr_results[0]\n\nfig, axis = plt.subplots(figsize=(5.5, 5))\npx.plot_utils.plot_line_family(axis, freq_vec, end_members, label_prefix='NFINDR endmember #')\naxis.set_title('NFINDR Endmembers', fontsize=14)\naxis.set_xlabel(x_label, fontsize=12)\naxis.set_ylabel(y_label, fontsize=12)\naxis.legend(bbox_to_anchor=[1.0,1.0], fontsize=12)\n\n# fully constrained least squares model:\nfcls = amp.FCLS()\n# Find abundances:\namap = fcls.map(data_mat[np.newaxis, :, :], end_members)\n\n# Reshaping amap\namap = np.reshape(np.squeeze(amap), (num_rows, num_cols, -1))\n\npx.plot_utils.plot_map_stack(amap, heading='NFINDR Abundance maps', cmap=plt.cm.inferno,\n color_bar_mode='single');"
]
......@@ -142,32 +161,13 @@
"collapsed": false
},
"outputs": [],
"execution_count": null,
"cell_type": "code",
"execution_count": null,
"source": [
"# Close and delete the h5_file\nh5_file.close()\nos.remove(data_file_path)"
]
}
],
"nbformat_minor": 0,
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"name": "python3",
"language": "python"
},
"language_info": {
"mimetype": "text/x-python",
"nbconvert_exporter": "python",
"file_extension": ".py",
"pygments_lexer": "ipython3",
"version": "3.5.2",
"codemirror_mode": {
"version": 3,
"name": "ipython"
},
"name": "python"
}
},
"nbformat": 4
"nbformat": 4,
"nbformat_minor": 0
}
\ No newline at end of file
docs/auto_examples/tutorial_03_multidimensional_data.py
View file @ 31c6b611
......@@ -218,45 +218,29 @@ print('Positions:', pos_dim_sizes, '\nSpectroscopic:', spec_dim_sizes)
# Let's assume that we are interested in visualizing the spectrograms at the first field of the second cycle at
# position - row:3 and column 2. There are two ways of accessing the data:
#
# 1. The easier method - reshape the data to N dimensions and slice the dataset
# 1. The hard method - find the spectroscopic and position indices of interest and slice the 2D dataset
#
# * This approach, while trivial, may not be suitable for large datasets which may or may not fit in memory
# 2. The easier method - reshape the data to N dimensions and slice the dataset
#
# 2. The harder method - find the spectroscopic and position indices of interest and slice the 2D dataset
# * This approach, while easy, may not be suitable for large datasets which may or may not fit in memory
#
# 3. The easiest method - use the PycroDataset class to slice the data
#
# * This method will only work for ``main`` datasets. We recommend using method 2 for slicing all others.
#
# Approach 1 - N-dimensional form
# -------------------------------
# We will use convenient pycroscopy function that safely reshapes the data to its N dimensional form with a single
# line. Note that while this approach appears simple on the surface, there are a fair number of lines of code that
# make up this function.
ds_nd, success, labels = px.hdf_utils.reshape_to_Ndims(h5_main, get_labels=True)
print('Shape of the N-dimensional dataset:', ds_nd.shape)
print(labels)
#########################################################################
# Now that we have the data in its original N dimensional form, we can easily slice the dataset:
spectrogram = ds_nd[2, 3, :, 0, :, 1]
# Now the spectrogram is of order (frequency x DC_Offset).
spectrogram = spectrogram.T
# Now the spectrogram is of order (DC_Offset x frequency)
fig, axis = plt. subplots()
axis.imshow(np.abs(spectrogram), origin='lower')
axis.set_xlabel('Frequency Index')
axis.set_ylabel('DC Offset Index')
axis.set_title('Spectrogram Amplitude');
#########################################################################
# Approach 2 - slicing the 2D matrix
# Approach 1 - slicing the 2D matrix
# ----------------------------------
#
# This approach is more hands-on and requires that we be very careful with the indexing and slicing. Nonetheless,
# This approach is hands-on and requires that we be very careful with the indexing and slicing. Nonetheless,
# the process is actually fairly intuitive. We rely entirely upon the spectroscopic and position ancillary datasets
# to find the indices for slicing the dataset. Unlike the main dataset, the ancillary datasets are very small and
# can be stored easily in memory. Once the slicing indices are calculated, we __only read the desired portion of
# `main` data to memory__. Thus the amount of data loaded into memory is only the amount that we absolutely need.
# __This is the only approach that can be applied to slice very large datasets without ovwhelming memory overheads__.
# The comments for each line explain the entire process comprehensively
#
# Get only the spectroscopic dimension names:
spec_dim_names = px.hdf_utils.get_attr(h5_spec_ind, 'labels')
......@@ -338,12 +322,35 @@ else:
print('We need to reshape the vector by the tuple:', spectrogram_shape)
# Reshaping from 1D to 2D:
spectrogram2 = np.reshape(np.squeeze(data_vec), spectrogram_shape)
spectrogram = np.reshape(np.squeeze(data_vec), spectrogram_shape)
#########################################################################
# Now that the spectrogram is indeed two dimensional, we can visualize it. This plot should match the one from the first
# approach.
# Now the spectrogram is of order (DC_Offset x frequency)
fig, axis = plt. subplots()
axis.imshow(np.abs(spectrogram), origin='lower')
axis.set_xlabel('Frequency Index')
axis.set_ylabel('DC Offset Index')
axis.set_title('Spectrogram Amplitude')
#########################################################################
# Approach 2 - N-dimensional form
# -------------------------------
# We will use convenient pycroscopy function that safely reshapes the data to its N dimensional form with a single
# line. Note that while this approach appears simple on the surface, there are a fair number of lines of code that
# make up this function.
ds_nd, success, labels = px.hdf_utils.reshape_to_Ndims(h5_main, get_labels=True)
print('Shape of the N-dimensional dataset:', ds_nd.shape)
print(labels)
#########################################################################
# Now that we have the data in its original N dimensional form, we can easily slice the dataset:
spectrogram2 = ds_nd[2, 3, :, :, 0, 1]
# Now the spectrogram is of order (frequency x DC_Offset).
spectrogram2 = spectrogram2.T
# Now the spectrogram is of order (DC_Offset x frequency)
fig, axis = plt. subplots()
axis.imshow(np.abs(spectrogram2), origin='lower')
......@@ -352,6 +359,46 @@ axis.set_ylabel('DC Offset Index')
axis.set_title('Spectrogram Amplitude');
#########################################################################
# Approach 3 - Using the PycroDataset
# -----------------------------------
# We will use the new PycroDataset class to create an N dimensional slice directly from the two dimensional
# data in the file.
#
# First we convert from an HDF5 Dataset to a PycroDataset
pd_main = px.PycroDataset(h5_main)
print(pd_main.shape)
#########################################################################
# As you can see, the data is still two dimensional. The PycroDataset has several attributes that will help with
# the slicing.
#
# Let's check the names and sizes of each dimension
print(pd_main.n_dim_labels)
print(pd_main.n_dim_sizes)
#########################################################################
# With this information, we can now get our data slice.
#
slice_dict = dict(X=[2], Y=[3], Field=[0], Cycle=[1])
nd_spec, success = pd_main.slice(**slice_dict)
print(success)
print(nd_spec.shape)
#########################################################################
# The slice is returned already in the N dimensional form. We just need to remove all the
# dimensions with length one, transpose it like in method 2, and plot.
#
spectrogram3 = nd_spec.squeeze().T
# Now the spectrogram is of order (DC_Offset x frequency)
fig, axis = plt. subplots()
axis.imshow(np.abs(spectrogram3), origin='lower')
axis.set_xlabel('Frequency Index')
axis.set_ylabel('DC Offset Index')
axis.set_title('Spectrogram Amplitude');
# Close and delete the h5_file
h5_file.close()
......
docs/auto_examples/tutorial_03_multidimensional_data.py.md5
View file @ 31c6b611
5bdff36c42774593e0b5e5bedbcee2cf
\ No newline at end of file
7b9e608c44816efc3e84fb6ee3b4bece
\ No newline at end of file
docs/auto_examples/tutorial_03_multidimensional_data.rst
View file @ 31c6b611
......@@ -396,68 +396,22 @@ Slicing the Main dataset
Let's assume that we are interested in visualizing the spectrograms at the first field of the second cycle at
position - row:3 and column 2. There are two ways of accessing the data:
1. The easier method - reshape the data to N dimensions and slice the dataset
1. The hard method - find the spectroscopic and position indices of interest and slice the 2D dataset
* This approach, while trivial, may not be suitable for large datasets which may or may not fit in memory
2. The easier method - reshape the data to N dimensions and slice the dataset
2. The harder method - find the spectroscopic and position indices of interest and slice the 2D dataset
Approach 1 - N-dimensional form
-------------------------------
We will use convenient pycroscopy function that safely reshapes the data to its N dimensional form with a single
line. Note that while this approach appears simple on the surface, there are a fair number of lines of code that
make up this function.
.. code-block:: python
ds_nd, success, labels = px.hdf_utils.reshape_to_Ndims(h5_main, get_labels=True)
print('Shape of the N-dimensional dataset:', ds_nd.shape)
print(labels)
.. rst-class:: sphx-glr-script-out
Out::
Shape of the N-dimensional dataset: (5, 5, 87, 64, 2, 2)
['X' 'Y' 'Frequency' 'DC_Offset' 'Field' 'Cycle']
Now that we have the data in its original N dimensional form, we can easily slice the dataset:
.. code-block:: python
spectrogram = ds_nd[2, 3, :, 0, :, 1]
# Now the spectrogram is of order (frequency x DC_Offset).
spectrogram = spectrogram.T
# Now the spectrogram is of order (DC_Offset x frequency)
fig, axis = plt. subplots()
axis.imshow(np.abs(spectrogram), origin='lower')
axis.set_xlabel('Frequency Index')
axis.set_ylabel('DC Offset Index')
axis.set_title('Spectrogram Amplitude');
* This approach, while easy, may not be suitable for large datasets which may or may not fit in memory
3. The easiest method - use the PycroDataset class to slice the data