Merge pull request #3 from Edinburgh-Genome-Foundry/dev

v0.2.7  --  fix xls / xlsx compatibility

.github/workflows/build.yml

@@ -0,0 +1,29 @@
+name: build
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.9
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.9"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest pytest-cov coveralls
+      - name: Install
+        run: |
+          pip install -e .
+      - name: Test with pytest
+        run: |
+          python -m pytest --cov plateo --cov-report term-missing
+      - name: Coveralls
+        run: coveralls
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          COVERALLS_SERVICE_NAME: github

.travis.yml

@@ -1,6 +1,6 @@
 language: python
 python:
-  - "3.6"
+  - "3.9"
 # command to install dependencies
 before_install:
   - pip install --upgrade pip

README.rst

@@ -6,9 +6,9 @@
     <br /><br />
     </p>
 
-.. image:: https://travis-ci.org/Edinburgh-Genome-Foundry/Plateo.svg?branch=master
-  :target: https://travis-ci.org/Edinburgh-Genome-Foundry/Plateo
-  :alt: Travis CI build status
+.. image:: https://github.com/Edinburgh-Genome-Foundry/Plateo/actions/workflows/build.yml/badge.svg
+    :target: https://github.com/Edinburgh-Genome-Foundry/Plateo/actions/workflows/build.yml
+    :alt: GitHub CI build status
 
 .. image:: https://coveralls.io/repos/github/Edinburgh-Genome-Foundry/Plateo/badge.svg?branch=master
   :target: https://coveralls.io/github/Edinburgh-Genome-Foundry/Plateo?branch=master
@@ -49,13 +49,13 @@ robot, we may be able to help too!
 Installation
 ------------
 
-Plateo can be installed by unzipping the source code in one directory and using this command: ::
+Plateo can be installed from the Python Package Index with PIP: ::
 
-    (sudo) python setup.py install
+    pip install plateo
 
-You can also install it directly from the Python Package Index with this command: ::
+It can also be installed by unzipping the source code in one directory and using this command: ::
 
-    (sudo) pip install plateo
+    python setup.py install
 
 
 Code organization

plateo/AssemblyPlan.py

@@ -8,19 +8,16 @@
 
 
 class AssemblyPlan:
-
     def __init__(self, assemblies, parts_data=None):
         if isinstance(assemblies, (list, tuple)):
             assemblies = OrderedDict(assemblies)
         self.assemblies = assemblies
         self.parts_data = parts_data
 
     def all_parts_used(self):
-        return sorted(set([
-            part
-            for assembly in self.assemblies.values()
-            for part in assembly
-        ]))
+        return sorted(
+            set([part for assembly in self.assemblies.values() for part in assembly])
+        )
 
     def parts_without_data(self):
         return {
@@ -30,14 +27,15 @@ def parts_without_data(self):
         }
 
     def assemblies_featuring(self, part):
-        return [name for (name, parts) in self.assemblies.items()
-                if part in parts]
+        return [name for (name, parts) in self.assemblies.items() if part in parts]
 
     def assemblies_with_records(self):
-        return OrderedDict([
-            (name, [self.get_part_data(p)['record'] for p in parts])
-            for name, parts in self.assemblies.items()
-        ])
+        return OrderedDict(
+            [
+                (name, [self.get_part_data(p)["record"] for p in parts])
+                for name, parts in self.assemblies.items()
+            ]
+        )
 
     def get_part_data(self, part_name):
         if part_name not in self.parts_data:
@@ -60,35 +58,50 @@ def rename_part(self, part_name, new_name):
                 self.parts_data[new_name] = self.parts_data.pop(part_name)
 
     @staticmethod
-    def from_spreadsheet(filepath=None, dataframe=None, sheet_name=0,
-                         header=None):
+    def from_spreadsheet(filepath=None, dataframe=None, sheet_name=0, header=None):
         if dataframe is None:
-            if filepath.lower().endswith('.csv'):
-                with open(filepath, 'r') as f:
-                    dataframe = pandas.DataFrame([
-                        line.split(',')
-                        for line in f.read().split('\n')
-                    ])
-            else:
-                dataframe = pandas.read_excel(filepath, sheet_name=sheet_name,
-                                              header=header)
-        return AssemblyPlan(OrderedDict([
-            (row[0], [
-                str(e)
-                for e in row[1:]
-                if str(e) not in ['-', 'nan', 'None', '']
-            ])
-            for i, row in dataframe.iterrows()
-            if str(row[0]).lower() not in ['nan', 'construct name',
-                                           'construct', 'none', '']
-        ]))
+            if filepath.lower().endswith(".csv"):
+                with open(filepath, "r") as f:
+                    dataframe = pandas.DataFrame(
+                        [line.split(",") for line in f.read().split("\n")]
+                    )
+            elif filepath.lower().endswith(".xls"):
+                dataframe = pandas.read_excel(
+                    filepath, sheet_name=sheet_name, header=header, engine="xlrd"
+                )
+            else:  # xlsx
+                dataframe = pandas.read_excel(
+                    filepath, sheet_name=sheet_name, header=header, engine="openpyxl"
+                )
+        return AssemblyPlan(
+            OrderedDict(
+                [
+                    (
+                        row[0],
+                        [
+                            str(e)
+                            for e in row[1:]
+                            if str(e) not in ["-", "nan", "None", ""]
+                        ],
+                    )
+                    for i, row in dataframe.iterrows()
+                    if str(row[0]).lower()
+                    not in ["nan", "construct name", "construct", "none", ""]
+                ]
+            )
+        )
 
     def to_spreadsheet(self, path):
         with open(path, "w") as f:
-            f.write("\n".join([("construct,parts")] + [
-                ",".join([asm] + parts)
-                for asm, parts in self.assemblies.items()
-            ]))
+            f.write(
+                "\n".join(
+                    [("construct,parts")]
+                    + [
+                        ",".join([asm] + parts)
+                        for asm, parts in self.assemblies.items()
+                    ]
+                )
+            )
 
     def assemblies_per_part(self):
         result = {}
@@ -107,14 +120,15 @@ def write_report(self, target):
         sequenticon_dict = None
         parts_length_dict = None
         first_part_data = list(self.parts_data.values())[0]
-        if 'record' in first_part_data:
-            sequenticons = sequenticon_batch([
-                self.get_part_data(p)['record']
-                for p in all_parts_used
-            ], output_format='html_image')
-            sequenticon_dict = OrderedDict([(name, icon)
-                                            for (name, icon) in sequenticons])
-        if (('record' in first_part_data) or ('size' in first_part_data)):
+        if "record" in first_part_data:
+            sequenticons = sequenticon_batch(
+                [self.get_part_data(p)["record"] for p in all_parts_used],
+                output_format="html_image",
+            )
+            sequenticon_dict = OrderedDict(
+                [(name, icon) for (name, icon) in sequenticons]
+            )
+        if ("record" in first_part_data) or ("size" in first_part_data):
             parts_length_dict = {
                 part: human_seq_size(self.get_part_length(part))
                 for part in all_parts_used
@@ -125,13 +139,13 @@ def write_report(self, target):
             sequenticon_dict=sequenticon_dict,
             parts_length_dict=parts_length_dict,
             all_parts_used=all_parts_used,
-            assemblies_per_part=assemblies_per_part
+            assemblies_per_part=assemblies_per_part,
         )
         report_writer.write_report(html, target)
 
     def get_part_length(self, part_name):
         data = self.get_part_data(part_name)
-        if 'size' in data:
-            return data['size']
+        if "size" in data:
+            return data["size"]
         else:
-            return len(data['record'])
+            return len(data["record"])

plateo/exporters/AssemblyPicklistGenerator.py

@@ -57,6 +57,10 @@ def make_picklist(
     ):
         source_wells = list(source_wells)
         destination_wells = list(destination_wells)
+
+        # The second statement would quietly discard assemblies, so we check for length:
+        if len(assembly_plan.assemblies) > len(destination_wells):
+            raise ValueError("There are more assemblies than destination wells!")
         destination_wells = destination_wells[: len(assembly_plan.assemblies)]
 
         part_wells = {}
@@ -82,14 +86,10 @@ def make_picklist(
                 {
                     "missing_parts": {
                         part: {
-                            "featured_in": assembly_plan.assemblies_featuring(
-                                part
-                            ),
+                            "featured_in": assembly_plan.assemblies_featuring(part),
                             "did_you_mean": [
                                 (name, str(part_wells[name]))
-                                for name in did_you_mean(
-                                    part, part_wells, min_score=50
-                                )
+                                for name in did_you_mean(part, part_wells, min_score=50)
                             ],
                         }
                         for part in missing_parts
@@ -103,14 +103,10 @@ def make_picklist(
             destination_well.data.construct = construct_name
             for part in parts:
                 source_well = part_wells[part]
-                volume = self.volume_from_well(
-                    source_well, assembly_plan.parts_data
-                )
+                volume = self.volume_from_well(source_well, assembly_plan.parts_data)
                 volume = round_at(volume, self.volume_rounding)
                 volume = max(volume, self.minimal_dispense_volume)
-                picklist.add_transfer(
-                    source_well, destination_well, volume=volume
-                )
+                picklist.add_transfer(source_well, destination_well, volume=volume)
 
         wells_over_desired_volume = []
         if self.complement_to is not None:
@@ -125,16 +121,13 @@ def make_picklist(
                     )
             if complement_well.is_empty:
                 raise TransferError(
-                    "Well with COMPLEMENT/WATER is empty: %s."
-                    % (complement_well)
+                    "Well with COMPLEMENT/WATER is empty: %s." % (complement_well)
                 )
             for well in destination_wells:
                 to_well = picklist.restricted_to(destination_well=well)
                 total_transfer_volume = to_well.total_transfered_volume()
                 complement_volume = (
-                    self.complement_to
-                    - total_transfer_volume
-                    - self.buffer_volume
+                    self.complement_to - total_transfer_volume - self.buffer_volume
                 )
                 if complement_volume < 0:
                     wells_over_desired_volume.append(well)
@@ -158,10 +151,7 @@ def make_picklist(
             {
                 "wells_over_desired_volume": wells_over_desired_volume,
                 "duplicates": {
-                    part_name: {
-                        "wells": wells,
-                        "selected": part_wells[part_name],
-                    }
+                    part_name: {"wells": wells, "selected": part_wells[part_name],}
                     for part_name, wells in duplicates.items()
                 },
             },
@@ -187,8 +177,7 @@ def get_part_molar_weight(self, part_data):
     def volume_from_well(self, well, parts_data):
         if well.content.volume == 0:
             raise ValueError(
-                ("Cannot get anything from well %s " % well)
-                + "which has a volume of 0"
+                ("Cannot get anything from well %s " % well) + "which has a volume of 0"
             )
         part_mol = self.part_mol
         part_g = self.part_g

plateo/exporters/reports/templates/assembly_mix_picklist_report.pug

@@ -1,4 +1,4 @@
-#sidebar: p Generated by Plateo version {{__version__}} on {{ pdf_tools.now() }}
+#sidebar: p Generated by Plateo version {{ version }} on {{ pdf_tools.now() }}
 
 .logos
   img(style='width: 120px;' src="file:///{{ plateo_logo_url }}")

plateo/exporters/reports/templates/assembly_plan_report.pug

@@ -1,4 +1,4 @@
-#sidebar: p Generated by Plateo version {{__version__}} on {{ pdf_tools.now() }}
+#sidebar: p Generated by Plateo version {{ version }} on {{ pdf_tools.now() }}
 
 .logos
   img(style='width: 120px;' src="file:///{{ plateo_logo_url }}")

plateo/parsers/picklist_from_labcyte_echo_picklist_file.py

@@ -3,9 +3,10 @@
 from ..containers import get_plate_class
 from ..PickList import PickList, Transfer
 
-def picklist_from_labcyte_echo_picklist_file(filename=None, dataframe=None,
-                                             source_plate="auto",
-                                             dest_plate="auto"):
+
+def picklist_from_labcyte_echo_picklist_file(
+    filename=None, dataframe=None, source_plate="auto", dest_plate="auto"
+):
     """Return a Picklist from an ECHO picklist file.
 
     Parameters
@@ -26,8 +27,11 @@ def picklist_from_labcyte_echo_picklist_file(filename=None, dataframe=None,
     if dataframe is None:
         if filename.lower().endswith(".csv"):
             dataframe = pandas.read_csv(filename)
-        else:
-            dataframe = pandas.read_excel(filename)
+        elif filename.lower().endswith(".xls"):
+            dataframe = pandas.read_excel(filename, engine="xlrd")
+        else:  # xlsx
+            dataframe = pandas.read_excel(filename, engine="openpyxl")
+
     if source_plate == "auto":
         nwells = infer_plate_size_from_wellnames(dataframe["Source Well"])
         source_plate = get_plate_class(nwells)()
@@ -36,9 +40,13 @@ def picklist_from_labcyte_echo_picklist_file(filename=None, dataframe=None,
         nwells = infer_plate_size_from_wellnames(dataframe["Destination Well"])
         dest_plate = get_plate_class(nwells)()
         dest_plate.name = "Destination"
-    return PickList([
-        Transfer(source_plate.wells[row["Source Well"]],
-                 dest_plate.wells[row["Destination Well"]],
-                 1e-9 * row["Volume"])
-        for i, row in dataframe.iterrows()
-    ])
+    return PickList(
+        [
+            Transfer(
+                source_plate.wells[row["Source Well"]],
+                dest_plate.wells[row["Destination Well"]],
+                1e-9 * row["Volume"],
+            )
+            for i, row in dataframe.iterrows()
+        ]
+    )