clean up for bruker process

not quite sure why I suppressed summary for sima - note to self

napeca/prepreprocess/.ipynb_checkpoints/bruker_data_process-checkpoint.ipynb

@@ -319,7 +319,7 @@
     "        start_idx = chunk_frames[0]\n",
     "        end_idx = chunk_frames[-1]+1\n",
     "\n",
-    "        data_to_save = tiff.imread(glob_list[start_idx:end_idx], key=0, is_ome=True)\n",
+    "        data_to_save = tiff.imread(glob_list[start_idx:end_idx], key=0, is_ome=True) # key indicates the page in the tiff\n",
     "\n",
     "        if save_format == 'tif':\n",
     "\n",
@@ -414,6 +414,11 @@
     "    analog_xml = ET.parse(xml_fpath).getroot()\n",
     "    return float(analog_xml.findall('Experiment')[0].find('Rate').text)\n",
     "\n",
+    "def read_analog_csv(csv_path):\n",
+    "    cycle_df = pd.read_csv(csv_path)\n",
+    "    cycle_df['Time(s)'] = cycle_df['Time(ms)'] / 1000.0\n",
+    "    cycle_df['cycle_num'] = float(re.findall('Cycle(\\d+)', csv_path)[0]) # get cycle # from filename\n",
+    "    return cycle_df\n",
     "\n",
     "\"\"\"\n",
     "Concatenate the analog input csv files if there are multiple cycles. Also make a dataframe with the \n",
@@ -438,11 +443,8 @@
     "    analog_concat = pd.DataFrame()\n",
     "    for cycle_idx, cycle_path_csv in enumerate(glob_analog_csv):\n",
     "\n",
-    "        cycle_df = pd.read_csv(cycle_path_csv)\n",
-    "        num_samples = len(cycle_df['Time(ms)'])\n",
-    "        cycle_df['Time(s)'] = cycle_df['Time(ms)']/1000.0\n",
+    "        cycle_df = self.read_analog_csv(cycle_path_csv)\n",
     "\n",
-    "        cycle_df['cycle_num'] = float(re.findall('Cycle(\\d+)', cycle_path_csv)[0]) # get cycle # from filename\n",
     "        if cycle_idx == 0: # initialize pd dataframe with first cycle's data\n",
     "            cycle_df['cumulative_time_ms'] = cycle_df['Time(ms)'].values\n",
     "            analog_concat = cycle_df\n",
@@ -456,16 +458,12 @@
     "    analog_concat.columns = analog_concat.columns.str.strip().str.lower().str.replace(' ', '_').str.replace('(', '_').str.replace(')', '')\n",
     "        \n",
     "    # loop through all analog columns and get the diff and threshold for event onsets\n",
-    "    analog_column_names = [column for column in analog_concat.columns if 'input' in column]\n",
-    "    num_analogs = len(analog_column_names)   \n",
+    "    analog_column_names = [column for column in analog_concat.columns if 'input' in column] \n",
     "    for idx, analog_column_name in enumerate(analog_column_names):\n",
-    "        \n",
     "        ttl_thresh = fparams['analog_ttl_thresh']\n",
-    "        if 'stim' in fparams['analog_names']: \n",
-    "            if idx == fparams['analog_names'].index('stim'):\n",
-    "                ttl_thresh = 0.01\n",
+    "        if 'stim' in fparams['analog_names'] and idx == fparams['analog_names'].index('stim'): \n",
+    "            ttl_thresh = 0.01\n",
     "            \n",
-    "                \n",
     "        print(analog_column_name)\n",
     "        print(ttl_thresh)\n",
     "        analog_concat[analog_column_name + '_diff'] = np.append(np.diff(analog_concat[analog_column_name]) > ttl_thresh, \n",
@@ -835,6 +833,35 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython2",
    "version": "2.7.16"
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
   }
  },
  "nbformat": 4,

napeca/prepreprocess/bruker_data_process.ipynb

@@ -414,6 +414,11 @@
     "    analog_xml = ET.parse(xml_fpath).getroot()\n",
     "    return float(analog_xml.findall('Experiment')[0].find('Rate').text)\n",
     "\n",
+    "def read_analog_csv(csv_path):\n",
+    "    cycle_df = pd.read_csv(csv_path)\n",
+    "    cycle_df['Time(s)'] = cycle_df['Time(ms)'] / 1000.0\n",
+    "    cycle_df['cycle_num'] = float(re.findall('Cycle(\\d+)', csv_path)[0]) # get cycle # from filename\n",
+    "    return cycle_df\n",
     "\n",
     "\"\"\"\n",
     "Concatenate the analog input csv files if there are multiple cycles. Also make a dataframe with the \n",
@@ -438,11 +443,8 @@
     "    analog_concat = pd.DataFrame()\n",
     "    for cycle_idx, cycle_path_csv in enumerate(glob_analog_csv):\n",
     "\n",
-    "        cycle_df = pd.read_csv(cycle_path_csv)\n",
-    "        num_samples = len(cycle_df['Time(ms)'])\n",
-    "        cycle_df['Time(s)'] = cycle_df['Time(ms)']/1000.0\n",
+    "        cycle_df = self.read_analog_csv(cycle_path_csv)\n",
     "\n",
-    "        cycle_df['cycle_num'] = float(re.findall('Cycle(\\d+)', cycle_path_csv)[0]) # get cycle # from filename\n",
     "        if cycle_idx == 0: # initialize pd dataframe with first cycle's data\n",
     "            cycle_df['cumulative_time_ms'] = cycle_df['Time(ms)'].values\n",
     "            analog_concat = cycle_df\n",
@@ -456,16 +458,12 @@
     "    analog_concat.columns = analog_concat.columns.str.strip().str.lower().str.replace(' ', '_').str.replace('(', '_').str.replace(')', '')\n",
     "        \n",
     "    # loop through all analog columns and get the diff and threshold for event onsets\n",
-    "    analog_column_names = [column for column in analog_concat.columns if 'input' in column]\n",
-    "    num_analogs = len(analog_column_names)   \n",
+    "    analog_column_names = [column for column in analog_concat.columns if 'input' in column] \n",
     "    for idx, analog_column_name in enumerate(analog_column_names):\n",
-    "        \n",
     "        ttl_thresh = fparams['analog_ttl_thresh']\n",
-    "        if 'stim' in fparams['analog_names']: \n",
-    "            if idx == fparams['analog_names'].index('stim'):\n",
-    "                ttl_thresh = 0.01\n",
+    "        if 'stim' in fparams['analog_names'] and idx == fparams['analog_names'].index('stim'): \n",
+    "            ttl_thresh = 0.01\n",
     "            \n",
-    "                \n",
     "        print(analog_column_name)\n",
     "        print(ttl_thresh)\n",
     "        analog_concat[analog_column_name + '_diff'] = np.append(np.diff(analog_concat[analog_column_name]) > ttl_thresh, \n",
@@ -835,6 +833,35 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython2",
    "version": "2.7.16"
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
   }
  },
  "nbformat": 4,

napeca/sima_extract_roi_sig.py

@@ -21,7 +21,7 @@ def extract(fpath):
     dataset = sima.ImagingDataset.load(os.path.join(fdir, fname + '_mc.sima'))  # reload motion-corrected dataset
     dataset.add_ROIs(rois, 'from_ImageJ')
     print('Extracting roi signals from %s' % fdir)
-    signals = dataset.extract(rois)
+    signals = dataset.extract(rois, save_summary=False)
     extracted_signals = np.asarray(signals['raw'])  # turn signals list into an np array
     np.save(os.path.join(fdir, fname + '_extractedsignals.npy'), extracted_signals)
     np.savetxt(os.path.join(fdir, fname + '_extractedsignals.csv'), np.squeeze(extracted_signals), delimiter=",")