Merge branch 'main' of https://github.com/catniplab/latent_dynamics_w…

…orkshop

01_latent_neural_states.ipynb

@@ -9,9 +9,10 @@
     "\n",
     "Let's analyze some neural data using popular dimensionality reduction methods.\n",
     "We will use the folloiwng methods with progressively better modeling assumptions.\n",
+    "\n",
     "- PCA (Principal Components Analysis)\n",
     "  - Gaussian observation\n",
-    "  - Independent identical gaussian noise per neuron\n",
+    "  - Independent identical gaussian noise per neuron  \n",
     "- GPFA (Gaussian Process Factor Analysis)\n",
     "  - Gaussian observation\n",
     "  - Unequal magnitude of noise per neuron\n",
@@ -219,16 +220,16 @@
    "outputs": [],
    "source": [
     "#Choose dataset\n",
-    "use_data = 'monkey'\n",
+    "use_data = 'vanderpol'\n",
     "\n",
     "if use_data=='vanderpol':\n",
     "    vdp_data = h5py.File(\"vanderpol/data/poisson_obs.h5\", 'r')\n",
     "    y = np.array(vdp_data['Y'])\n",
+    "    dt = 5e-3  # time bin size\n",
     "    gaussian_filter_sigma = 12.0\n",
     "    nTrial = vdp_data['X'].shape[0]\n",
     "    nT = vdp_data['X'].shape[1]\n",
     "    nNeuron = vdp_data['Y'].shape[2]\n",
-    "    dt = 5e-3  # time bin size\n",
     "    n_latent = 2\n",
     "\n",
     "elif use_data=='monkey':\n",
@@ -239,8 +240,10 @@
     "    nTrial = m5['pos-train'].shape[0]\n",
     "    nT = m5['pos-train'].shape[1]\n",
     "    nNeuron = m5['spk-train'].shape[2]\n",
-    "    dt = 0.005  # 5 ms bin\n",
     "    n_latent = n_latent_mc_maze\n",
+    "    \n",
+    "else:\n",
+    "    raise Exceptiontion(\"Typo?!\")\n",
     "\n",
     "T = dt * nT"
    ]