Add flake8 to earthpy (#520)

* add flake 8 * update change log * black * not in * flake 8 * docstring update
earthlab · Mar 26, 2020 · 96657a1 · 96657a1
1 parent e4bc8c5
commit 96657a1
Show file tree

Hide file tree

Showing 18 changed files with 140 additions and 94 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -3,4 +3,9 @@ repos:
   rev: stable
   hooks:
   - id: black
-    language_version: python3.6
+    language_version: python3.7
+-   repo: https://gitlab.com/pycqa/flake8
+    rev: 3.7.7
+    hooks:
+    -   id: flake8
+        language: python_venv
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,6 +6,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+* Add flake 8 (@lwasser, #519)
 * Remove conda envt for RTD build (@lwasser, #518)
 * Deprecate clip function from earthpy given it's moved to geopandas now (@nkorinek, #510)
 * Fix twitter flood data key in get_data (@lwasser, #512)

diff --git a/earthpy/clip.py b/earthpy/clip.py
@@ -6,6 +6,8 @@
 
 """
 
+import sys
+
 
 # @deprecate
 def _clip_points(shp, clip_obj):

diff --git a/earthpy/io.py b/earthpy/io.py
@@ -17,6 +17,7 @@
 
 # Data URLs, structured as {'week_name': [(URL, FILENAME, FILETYPE)]}
 # If zipfile, tarfile, etc, unzip to a folder w/ the name
+
 DATA_URLS = {
     "co-flood-extras": [
         (
@@ -51,12 +52,18 @@
         "zip",
     ),
     "cs-test-naip": (
-        "https://ndownloader.figshare.com/files/10960211?private_link=18f892d9f3645344b2fe",
+        (
+            "https://ndownloader.figshare.com/files/10960211?"
+            "private_link=18f892d9f3645344b2fe"
+        ),
         ".",
         "zip",
     ),
     "cs-test-landsat": (
-        "https://ndownloader.figshare.com/files/10960214?private_link=fbba903d00e1848b423e",
+        (
+            "https://ndownloader.figshare.com/files/10960214?private_link"
+            "=fbba903d00e1848b423e"
+        ),
         ".",
         "zip",
     ),

diff --git a/earthpy/mask.py b/earthpy/mask.py
@@ -109,16 +109,16 @@ def _create_mask(mask_arr, vals):
     Returns
     -----------
     arr : numpy array
-        A numpy array populated with 1's where the mask is applied (a Boolean True)
-        and a 0 where no masking will be done.
+        A numpy array populated with 1's where the mask is applied (a Boolean
+        True) and a 0 where no masking will be done.
     """
 
     try:
         vals.sort()
     except AttributeError:
         raise AttributeError("Values should be provided as a list")
 
-    # For some reason if you don't copy this here, it magically changes the input
+    # For some reason if you don't copy this here, it changes the input
     # qa layer to a boolean in the main environment.
     new_mask_arr = mask_arr.copy()
     unique_vals = np.unique(new_mask_arr).tolist()
@@ -152,7 +152,8 @@ def _apply_mask(arr, input_mask):
     Returns
     -----------
     numpy array
-        The original numpy array with the mask applied to cover up issue pixels.
+        The original numpy array with the mask applied to cover up issue
+        pixels.
     """
 
     # Test if input_mask is numpy array w values == 1 for masked
@@ -172,10 +173,11 @@ def _apply_mask(arr, input_mask):
 def mask_pixels(arr, mask_arr, vals=None):
     """Apply a mask to an input array.
 
-    Masks values in an n-dimensional input array (arr) based on input 1-dimensional
-    array (mask_arr). If mask_arr is provided in a boolean format, it is used as a mask.
-    If mask_arr is provided as a non-boolean format and values to mask (vals) are provided,
-    a Boolean masked array is created from the mask_arr and the indicated vals to mask, and
+    Masks values in an n-dimensional input array (arr) based on input
+    1-dimensional array (mask_arr). If mask_arr is provided in a boolean
+    format, it is used as a mask. If mask_arr is provided as a non-boolean
+    format and values to mask (vals) are provided, a Boolean masked array is
+    created from the mask_arr and the indicated vals to mask, and
     then this new 1-dimensional masked array is used to mask the input arr.
 
     This function is useful when masking cloud and other unwanted pixels.
@@ -194,8 +196,9 @@ def mask_pixels(arr, mask_arr, vals=None):
     Returns
     -------
     arr : numpy array
-        A numpy array populated with 1's where the mask is applied (a Boolean True)
-        and the original numpy array's value where no masking was done.
+        A numpy array populated with 1's where the mask is applied (a
+        Boolean True) and the original numpy array's value where no masking
+        was done.
 
     Example
     -------

diff --git a/earthpy/plot.py b/earthpy/plot.py
@@ -19,12 +19,14 @@
 def colorbar(mapobj, size="3%", pad=0.09):
     """Adjust colorbar height to match the matplotlib axis height.
 
-    NOTE: This function requires matplotlib v 3.0.1 or greater or v 2.9 or lower to run properly.
+    NOTE: This function requires matplotlib v 3.0.1 or greater or v 2.9 or
+    lower to run properly.
 
     Parameters
     ----------
     mapobj : matplotlib axis object
-        The image that the colorbar will be representing as a matplotlib axis object.
+        The image that the colorbar will be representing as a matplotlib axis
+        object.
     size : char (default = "3%")
         The percent width of the colorbar relative to the plot.
     pad : int (default = 0.09)
@@ -109,13 +111,13 @@ def _plot_image(
     ax : Matplotlib axes object (Optional)
         Matplotlib axis object to plot image.
     alpha : float (optional)
-        The alpha value for the plot. This will help adjust the transparency of the
-        plot to the desired level.
+        The alpha value for the plot. This will help adjust the transparency of
+        the plot to the desired level.
     norm : matplotlib Normalize object (Optional)
-        The normalized boundaries for custom values coloring. NOTE: For this argument
-        to work, the scale argument MUST be set to false. Otherwise, the values will
-        just be scaled from 0-255
-        
+        The normalized boundaries for custom values coloring. NOTE: For this
+        argument to work, the scale argument MUST be set to false. Otherwise,
+        the values will just be scaled from 0-255
+
     Returns
     ----------
     ax : matplotlib.axes object
@@ -185,13 +187,13 @@ def plot_bands(
     vmax : Int (Optional)
         Specify the vmax to scale imshow() plots.
     alpha : float (optional)
-        The alpha value for the plot. This will help adjust the transparency of the
-        plot to the desired level.
+        The alpha value for the plot. This will help adjust the transparency
+        of the plot to the desired level.
     norm : matplotlib Normalize object (Optional)
-        The normalized boundaries for custom values coloring. NOTE: For this argument
-        to work, the scale argument MUST be set to false. Because of this, the 
-        function will automatically set scale to false, even if the user manually
-        sets scale to true. 
+        The normalized boundaries for custom values coloring. NOTE: For this
+        argument to work, the scale argument MUST be set to false. Because
+        of this, the function will automatically set scale to false,
+        even if the user manually sets scale to true.
 
     Returns
     ----------
@@ -366,7 +368,8 @@ def plot_rgb(
     title : string (optional)
         The intended title of the plot.
     stretch : Boolean (optional)
-        Application of a linear stretch. If set to True, a linear stretch will be applied.
+        Application of a linear stretch. If set to True, a linear stretch will
+        be applied.
 
     Returns
     ----------
@@ -384,7 +387,7 @@ def plot_rgb(
         >>> from earthpy.io import path_to_example
         >>> with rio.open(path_to_example('rmnp-rgb.tif')) as src:
         ...     img_array = src.read()
-        >>> # Before you plot, ensure that the input array does not have nodata values like -9999
+        >>> # Ensure the input array doesn't have nodata values like -9999
         >>> ep.plot_rgb(img_array)
         <matplotlib.axes._subplots.AxesSubplot object at 0x...
 
@@ -468,12 +471,12 @@ def hist(
     ylabel : str (optional)
         The text to print on the y axis.
     hist_range : tuple (optional)
-        The lower and upper range of the bins. Lower and upper outliers are ignored.
-        If not provided, range is (x.min(), x.max()).
+        The lower and upper range of the bins. Lower and upper outliers are
+        ignored. If not provided, range is (x.min(), x.max()).
         Range has no effect if bins is a sequence.
     alpha : float (optional)
-        The alpha value for the plot. This will help adjust the transparency of the
-        plot to the desired level.
+        The alpha value for the plot. This will help adjust the transparency
+        of the plot to the desired level.
 
     Returns
     ----------
@@ -566,7 +569,8 @@ def hist(
         if title:
             if len(title) > 1:
                 raise ValueError(
-                    "You have one array to plot but more than one title. Please provide a single title value."
+                    "You have one array to plot but more than one title. "
+                    "Please provide a single title value."
                 )
 
         # Plot all bands
@@ -591,7 +595,8 @@ def hist(
 
 def make_col_list(unique_vals, nclasses=None, cmap=None):
     """
-    Convert a matplotlib named colormap into a discrete list of n-colors in RGB format.
+    Convert a matplotlib named colormap into a discrete list of n-colors in
+    RGB format.
 
     Parameters
     ----------
@@ -732,7 +737,7 @@ def draw_legend(im_ax, bbox=(1.05, 1), titles=None, cmap=None, classes=None):
         )
 
     patches = [
-        mpatches.Patch(color=colors[i], label="{l}".format(l=titles[i]))
+        mpatches.Patch(color=colors[i], label="{lab}".format(lab=titles[i]))
         for i in range(len(titles))
     ]
     # Get the axis for the legend

diff --git a/earthpy/spatial.py b/earthpy/spatial.py
@@ -60,21 +60,22 @@ def extent_to_json(ext_obj):
 
 
 def normalized_diff(b1, b2):
-    """Take two n-dimensional numpy arrays and calculate the normalized difference.
+    """Take two n-dimensional numpy arrays and calculate the normalized
+    difference.
 
     Math will be calculated (b1-b2) / (b1 + b2).
 
     Parameters
     ----------
     b1, b2 : numpy arrays
-        Two numpy arrays that will be used to calculate the normalized difference.
-        Math will be calculated (b1-b2) / (b1+b2).
+        Two numpy arrays that will be used to calculate the normalized
+        difference. Math will be calculated (b1-b2) / (b1+b2).
 
     Returns
     ----------
     n_diff : numpy array
-        The element-wise result of (b1-b2) / (b1+b2) calculation. Inf values are set
-        to nan. Array returned as masked if result includes nan values.
+        The element-wise result of (b1-b2) / (b1+b2) calculation. Inf values
+        are set to nan. Array returned as masked if result includes nan values.
 
     Examples
     --------
@@ -106,7 +107,8 @@ def normalized_diff(b1, b2):
     # Set inf values to nan and provide custom warning
     if np.isinf(n_diff).any():
         warnings.warn(
-            "Divide by zero produced infinity values that will be replaced with nan values",
+            "Divide by zero produced infinity values that will be replaced "
+            "with nan values",
             Warning,
         )
         n_diff[np.isinf(n_diff)] = np.nan
@@ -130,7 +132,8 @@ def stack(band_paths, out_path="", nodata=None):
         A path with a file name for the output stacked raster
         tif file.
     nodata : numeric (optional)
-        A value (int or float) that represents invalid or missing values to mask in the output.
+        A value (int or float) that represents invalid or missing values to
+        mask in the output.
 
     Returns
     ----------
@@ -139,8 +142,8 @@ def stack(band_paths, out_path="", nodata=None):
         numpy array
             N-dimensional array created by stacking the raster files provided.
         rasterio profile object
-            A rasterio profile object containing the updated spatial metadata for
-            the stacked numpy array.
+            A rasterio profile object containing the updated spatial metadata
+            for the stacked numpy array.
 
     Example
     -------
@@ -171,7 +174,8 @@ def stack(band_paths, out_path="", nodata=None):
 
     if len(band_paths) < 2:
         raise ValueError(
-            "The list of file paths is empty. You need at least 2 files to create a stack."
+            "The list of file paths is empty. You need at least 2 files to "
+            "create a stack."
         )
 
     # Invalid filename specified and write_raster == True.
@@ -211,7 +215,8 @@ def stack(band_paths, out_path="", nodata=None):
 
         if not len(set(dest_shps)) == 1:
             raise ValueError(
-                "Please ensure all source rasters have same dimensions (nrows, ncols)."
+                "Please ensure all source rasters have same dimensions "
+                "(nrows, ncols)."
             )
 
         # Update band count
@@ -240,13 +245,12 @@ def stack(band_paths, out_path="", nodata=None):
             # Valid output path checked above
             file_fmt = os.path.basename(out_path).split(".")[-1]
 
-            # Check if the file format for output is the same as the source driver
+            # Check that file format for output is the same as source driver
             rio_driver = sources[0].profile["driver"]
-            if not file_fmt in rio_driver.lower():
+            if file_fmt not in rio_driver.lower():
                 raise ValueError(
-                    "Source data is {}. Please specify corresponding output extension.".format(
-                        rio_driver
-                    )
+                    "Source data is {}. Please specify corresponding output "
+                    "extension.".format(rio_driver)
                 )
 
             # Write stacked gtif file
@@ -299,7 +303,7 @@ def _stack_bands(sources, write_raster=False, dest=None):
         for src in sources:
             src.profile
 
-    except AttributeError as ae:
+    except AttributeError:
         raise AttributeError("The sources object should be Dataset Reader")
         sys.exit()
 
@@ -441,10 +445,10 @@ def crop_all(
         >>> import geopandas as gpd
         >>> from earthpy.io import path_to_example
         >>> band_fnames = ["red.tif", "green.tif", "blue.tif"]
-        >>> band_paths = [path_to_example(fname) for fname in band_fnames]
+        >>> paths = [path_to_example(fname) for fname in band_fnames]
         >>> rmnp = gpd.read_file(path_to_example("rmnp.shp"))
-        >>> output_dir = os.path.commonpath(band_paths)
-        >>> output_files = es.crop_all(band_paths, output_dir, rmnp, overwrite=True)
+        >>> out_dir = os.path.commonpath(paths)
+        >>> output_files = es.crop_all(paths, out_dir, rmnp, overwrite=True)
         >>> len(output_files)
         3
         >>> os.path.isfile(output_files[0])
@@ -545,12 +549,14 @@ def bytescale(data, high=255, low=0, cmin=None, cmax=None):
         raise ValueError("`cmax` should be larger than `cmin`.")
     elif crange == 0:
         raise ValueError(
-            "`cmax` and `cmin` should not be the same value. Please specify `cmax` > `cmin`"
+            "`cmax` and `cmin` should not be the same value. Please specify "
+            "`cmax` > `cmin`"
         )
 
     scale = float(high - low) / crange
 
-    # If cmax is less than the data max, then this scale parameter will create data > 1.0. clip the data to cmax first.
+    # If cmax is less than the data max, then this scale parameter will create
+    # data > 1.0. clip the data to cmax first.
     data[data > cmax] = cmax
     bytedata = (data - cmin) * scale + low
     return (bytedata.clip(low, high) + 0.5).astype("uint8")
@@ -562,7 +568,7 @@ def hillshade(arr, azimuth=30, altitude=30):
     Parameters
     ----------
     arr : numpy array of shape (rows, columns)
-        Numpy array containing elevation values to be used to created hillshade.
+        Numpy array with elevation values to be used to created hillshade.
     azimuth : float (default=30)
         The desired azimuth for the hillshade.
     altitude : float (default=30)
@@ -594,7 +600,7 @@ def hillshade(arr, azimuth=30, altitude=30):
     """
     try:
         x, y = np.gradient(arr)
-    except:
+    except ValueError:
         raise ValueError("Input array should be two-dimensional")
 
     if azimuth <= 360.0: