diff --git a/dipy/align/streamlinear.py b/dipy/align/streamlinear.py
index 4fffcd703a..7fb169c86a 100644
--- a/dipy/align/streamlinear.py
+++ b/dipy/align/streamlinear.py
@@ -1001,7 +1001,7 @@ def check_range(streamline, gt=greater_than, lt=less_than):
 # SLR on QuickBundles centroids and some thresholding see
 # Garyfallidis et al. Recognition of white matter
 # bundles using local and global streamline-based registration and
-# clustering, Neuroimage, 2017.
+# clustering, NeuroImage, 2017.
 whole_brain_slr = slr_with_qbx
 
 
diff --git a/dipy/align/tests/test_imaffine.py b/dipy/align/tests/test_imaffine.py
index 336b9ec008..a91a2368a3 100644
--- a/dipy/align/tests/test_imaffine.py
+++ b/dipy/align/tests/test_imaffine.py
@@ -321,7 +321,7 @@ def test_mi_gradient():
         # Compute the gradient with the implementation under test
         actual = mi_metric.gradient(theta)
 
-        # Compute the gradient using finite-diferences
+        # Compute the gradient using finite-differences
         n = transform.get_number_of_parameters()
         expected = np.empty(n, dtype=np.float64)
 
diff --git a/dipy/align/tests/test_imwarp.py b/dipy/align/tests/test_imwarp.py
index 1580e175f2..7ec7292d0b 100644
--- a/dipy/align/tests/test_imwarp.py
+++ b/dipy/align/tests/test_imwarp.py
@@ -107,7 +107,7 @@ def test_diffeomorphic_map_2d():
 
         # Now test the nearest neighbor interpolation
         warped = diff_map.transform(moving_image, 'nearest')
-        # compare the images (now we dont have to worry about precision,
+        # compare the images (now we don't have to worry about precision,
         # it is n.n.)
         assert_array_almost_equal(warped, expected)
 
@@ -324,7 +324,7 @@ def test_optimizer_exceptions():
     # Verify the default iterations list
     assert_array_equal(optimizer.level_iters, [100, 100, 25])
 
-    # Verify exception thrown when attepting to fit the energy profile without
+    # Verify exception thrown when attempting to fit the energy profile without
     # enough data
     assert_raises(ValueError, optimizer._get_energy_derivative)
 
diff --git a/dipy/align/tests/test_sumsqdiff.py b/dipy/align/tests/test_sumsqdiff.py
index 597caabae5..6ee9b073b8 100644
--- a/dipy/align/tests/test_sumsqdiff.py
+++ b/dipy/align/tests/test_sumsqdiff.py
@@ -27,7 +27,7 @@ def iterate_residual_field_ssd_2d(delta_field, sigmasq_field, grad, target,
     for r in range(nrows):
         for c in range(ncols):
             sigmasq = sigmasq_field[r, c] if sigmasq_field is not None else 1
-            # This has to be done inside the neste loops because
+            # This has to be done inside the nested loops because
             # some d[...] may have been previously modified
             nn = 0
             y[:] = 0
@@ -212,12 +212,12 @@ def test_compute_residual_displacement_field_ssd_2d():
         else:
             expected = target.copy().astype(np.float64)
 
-        # Expected residuals when sigma != infinte
+        # Expected residuals when sigma != infinity
         expected[inf_sigma == 0, 0] -= grad_G[inf_sigma == 0, 0] * \
             dp[inf_sigma == 0] + sigma_field[inf_sigma == 0] * s[inf_sigma == 0, 0]
         expected[inf_sigma == 0, 1] -= grad_G[inf_sigma == 0, 1] * \
             dp[inf_sigma == 0] + sigma_field[inf_sigma == 0] * s[inf_sigma == 0, 1]
-        # Expected residuals when sigma == infinte
+        # Expected residuals when sigma == infinity
         expected[inf_sigma == 1] = -1.0 * s[inf_sigma == 1]
 
         # Test residual field computation starting with residual = None
@@ -355,11 +355,11 @@ def test_compute_residual_displacement_field_ssd_3d():
         else:
             expected = target.copy().astype(np.float64)
 
-        # Expected residuals when sigma != infinte
+        # Expected residuals when sigma != infinity
         for i in range(3):
             expected[inf_sigma == 0, i] -= grad_G[inf_sigma == 0, i] * \
                 dp[inf_sigma == 0] + sigma_field[inf_sigma == 0] * s[inf_sigma == 0, i]
-        # Expected residuals when sigma == infinte
+        # Expected residuals when sigma == infinity
         expected[inf_sigma == 1] = -1.0 * s[inf_sigma == 1]
 
         # Test residual field computation starting with residual = None
diff --git a/dipy/align/tests/test_transforms.py b/dipy/align/tests/test_transforms.py
index d2354ba0db..06d4f707f8 100644
--- a/dipy/align/tests/test_transforms.py
+++ b/dipy/align/tests/test_transforms.py
@@ -229,9 +229,9 @@ def test_invalid_transform():
     # Note: users should not attempt to use the base class Transform:
     # they should get an instance of one of its derived classes from the
     # regtransforms dictionary (the base class is not contained there)
-    # If for some reason the user instanciates it and attempts to use it,
+    # If for some reason the user instantiates it and attempts to use it,
     # however, it will raise exceptions when attempting to retrieve its
-    # jacobian, identity parameters or its matrix representation. It will
+    # Jacobian, identity parameters or its matrix representation. It will
     # return -1 if queried about its dimension or number of parameters
     transform = Transform()
     theta = np.ndarray(3)
diff --git a/dipy/core/tests/test_geometry.py b/dipy/core/tests/test_geometry.py
index 49fe02e690..461bbb4f83 100644
--- a/dipy/core/tests/test_geometry.py
+++ b/dipy/core/tests/test_geometry.py
@@ -270,7 +270,7 @@ def test_perpendicular_directions():
     for vector_v in vectors_v:
         pd = perpendicular_directions(vector_v, num=num, half=False)
 
-        # see if length of pd is equal to the number of intendend samples
+        # see if length of pd is equal to the number of intended samples
         assert_equal(num, len(pd))
 
         # check if all directions are perpendicular to vector v
diff --git a/dipy/core/tests/test_gradients.py b/dipy/core/tests/test_gradients.py
index a1b75d15fc..3121a640b3 100644
--- a/dipy/core/tests/test_gradients.py
+++ b/dipy/core/tests/test_gradients.py
@@ -152,7 +152,7 @@ def test_gradient_table_from_bvals_bvecs():
     gt = gradient_table_from_bvals_bvecs(bvals, new_bvecs, b0_threshold=0)
     npt.assert_array_equal(gt.bvecs, bvecs)
 
-    # Bvalue > 0 for non-unit vector
+    # b-value > 0 for non-unit vector
     bad_bvals = [2, 1, 2, 3, 4, 5, 6, 0]
     npt.assert_raises(ValueError, gradient_table_from_bvals_bvecs, bad_bvals,
                       bvecs, b0_threshold=0.)
@@ -326,7 +326,7 @@ def test_nan_bvecs():
 def test_generate_bvecs():
     """Tests whether we have properly generated bvecs.
     """
-    # Test if the generated bvectors are unit vectors
+    # Test if the generated b-vectors are unit vectors
     bvecs = generate_bvecs(100)
     norm = [np.linalg.norm(v) for v in bvecs]
     npt.assert_almost_equal(norm, np.ones(100))
@@ -351,7 +351,7 @@ def test_round_bvals():
     b = round_bvals(bvals, bmag=0)
     npt.assert_array_almost_equal(bvals, b)
 
-    # Case that b-valuea are in ms/um2
+    # Case that b-value are in ms/um2
     bvals = np.array([0.995, 0.995, 0.995, 0.995, 2.005, 2.005, 2.005, 2.005,
                       0])
     b = round_bvals(bvals)
diff --git a/dipy/denoise/noise_estimate.py b/dipy/denoise/noise_estimate.py
index afcfc789ce..121cf18db9 100644
--- a/dipy/denoise/noise_estimate.py
+++ b/dipy/denoise/noise_estimate.py
@@ -57,7 +57,7 @@ def piesno(data, N, alpha=0.01, l=100, itermax=100, eps=1e-5,
         reached if two subsequent estimates are smaller than eps.
 
     return_mask : bool
-        If True, return a mask identyfing all the pure noise voxel
+        If True, return a mask identifying all the pure noise voxel
         that were found.
 
     Returns
@@ -171,7 +171,7 @@ def _piesno_3D(data, N, alpha=0.01, l=100, itermax=100, eps=1e-5,
         Default: 1e-5.
 
     return_mask : bool (optional)
-        If True, return a mask identyfing all the pure noise voxel
+        If True, return a mask identifying all the pure noise voxel
         that were found. Default: False.
 
     initial_estimation : float (optional)
diff --git a/dipy/denoise/shift_twist_convolution.pyx b/dipy/denoise/shift_twist_convolution.pyx
index 3debe71dfb..c5dd3c47e5 100644
--- a/dipy/denoise/shift_twist_convolution.pyx
+++ b/dipy/denoise/shift_twist_convolution.pyx
@@ -179,7 +179,7 @@ cdef double [:, :, :, ::1] perform_convolution (double [:, :, :, ::1] odfs,
 
     with nogil:
 
-        # loop over ODFs cx,cy,cz,corient --> y and v
+        # loop over ODFs cx,cy,cz,orient --> y and v
         for corient in prange(OR1, schedule='guided'):
             for cx in range(nx):
                 for cy in range(ny):
diff --git a/dipy/denoise/tests/test_lpca.py b/dipy/denoise/tests/test_lpca.py
index 8295b914de..50236bec1c 100644
--- a/dipy/denoise/tests/test_lpca.py
+++ b/dipy/denoise/tests/test_lpca.py
@@ -27,7 +27,7 @@ def rfiw_phantom(gtab, snr=None):
     slice_ind[3, 4:7, :] = 8
     slice_ind[3, 7, :] = 9
 
-    # Define tisse diffusion parameters
+    # Define tissue diffusion parameters
     # Restricted diffusion
     ADr = 0.99e-3
     RDr = 0.0
@@ -54,7 +54,7 @@ def rfiw_phantom(gtab, snr=None):
     # tissue volume fractions have to be adjusted to the measured f values when
     # constant S0 are assumed constant. Doing this correction, simulations will
     # be analogous to simulates that S0 are different for each media. (For more
-    # datails on this contact the phantom designer)
+    # details on this contact the phantom designer)
     f1 = f * S1 / S0
 
     mevals = np.array([[ADr, RDr, RDr], [ADh, RDh, RDh],
@@ -189,7 +189,7 @@ def test_phantom():
     gtab = gen_gtab()
     DWI_clean = rfiw_phantom(gtab, snr=None)
     DWI, sigma = rfiw_phantom(gtab, snr=30)
-    # To test without rician correction
+    # To test without Rician correction
     temp = (DWI_clean / sigma)**2
     DWI_clean_wrc = (sigma * np.sqrt(np.pi / 2) * np.exp(-0.5 * temp) *
                      ((1 + 0.5 * temp) * sps.iv(0, 0.25 * temp) + 0.5 * temp *
diff --git a/dipy/direction/tests/test_pmf.py b/dipy/direction/tests/test_pmf.py
index 51a114a4b2..d3f376cf33 100644
--- a/dipy/direction/tests/test_pmf.py
+++ b/dipy/direction/tests/test_pmf.py
@@ -67,7 +67,7 @@ def test_boot_pmf():
     npt.assert_equal(len(hsph_updated.vertices), no_boot_pmf.shape[0])
     npt.assert_array_almost_equal(no_boot_pmf, model_pmf)
 
-    # test model sherical harminic order different than bootstrap order
+    # test model spherical harmonic order different than bootstrap order
     with warnings.catch_warnings(record=True) as w:
         warnings.simplefilter("always", category=UserWarning)
         csd_model = ConstrainedSphericalDeconvModel(gtab, None, sh_order=6)
diff --git a/dipy/reconst/dki.py b/dipy/reconst/dki.py
index 66c75ece22..14ddf1d755 100644
--- a/dipy/reconst/dki.py
+++ b/dipy/reconst/dki.py
@@ -240,7 +240,7 @@ def _F1m(a, b, c):
     # Only computes F1 in voxels that have all eigenvalues larger than zero
     cond0 = _positive_evals(a, b, c)
 
-    # Apply formula for non problematic plaussible cases, i.e. a!=b and a!=c
+    # Apply formula for non problematic plausible cases, i.e. a!=b and a!=c
     cond1 = np.logical_and(cond0, np.logical_and(abs(a - b) >= a * er,
                                                  abs(a - c) >= a * er))
     if np.sum(cond1) != 0:
@@ -254,7 +254,7 @@ def _F1m(a, b, c):
                      (3 * L1**2 - L1 * L2 - L1 * L3 - L2 * L3) /
                      (3 * L1 * np.sqrt(L2 * L3)) * RDm - 1)
 
-    # Resolve possible sigularity a==b
+    # Resolve possible singularity a==b
     cond2 = np.logical_and(cond0, np.logical_and(abs(a - b) < a * er,
                                                  abs(a - c) > a * er))
     if np.sum(cond2) != 0:
@@ -262,7 +262,7 @@ def _F1m(a, b, c):
         L3 = c[cond2]
         F1[cond2] = _F2m(L3, L1, L1) / 2.
 
-    # Resolve possible sigularity a==c
+    # Resolve possible singularity a==c
     cond3 = np.logical_and(cond0, np.logical_and(abs(a - c) < a * er,
                                                  abs(a - b) > a * er))
     if np.sum(cond3) != 0:
@@ -270,7 +270,7 @@ def _F1m(a, b, c):
         L2 = b[cond3]
         F1[cond3] = _F2m(L2, L1, L1) / 2
 
-    # Resolve possible sigularity a==b and a==c
+    # Resolve possible singularity a==b and a==c
     cond4 = np.logical_and(cond0, np.logical_and(abs(a - c) < a * er,
                                                  abs(a - b) < a * er))
     if np.sum(cond4) != 0:
@@ -328,7 +328,7 @@ def _F2m(a, b, c):
     # Only computes F2 in voxels that have all eigenvalues larger than zero
     cond0 = _positive_evals(a, b, c)
 
-    # Apply formula for non problematic plaussible cases, i.e. b!=c
+    # Apply formula for non problematic plausible cases, i.e. b!=c
     cond1 = np.logical_and(cond0, (abs(b - c) > b * er))
     if np.sum(cond1) != 0:
         L1 = a[cond1]
@@ -340,14 +340,14 @@ def _F2m(a, b, c):
                     (((L2 + L3) / (np.sqrt(L2 * L3))) * RF +
                      ((2. * L1 - L2 - L3) / (3. * np.sqrt(L2 * L3))) * RD - 2.)
 
-    # Resolve possible sigularity b==c
+    # Resolve possible singularity b==c
     cond2 = np.logical_and(cond0, np.logical_and(abs(b - c) < b * er,
                                                  abs(a - b) > b * er))
     if np.sum(cond2) != 0:
         L1 = a[cond2]
         L3 = (c[cond2] + b[cond2]) / 2.
 
-        # Cumpute alfa [1]_
+        # Compute alfa [1]_
         x = 1. - (L1 / L3)
         alpha = np.zeros(len(L1))
         for i in range(len(x)):
@@ -360,7 +360,7 @@ def _F2m(a, b, c):
             6. * ((L1 + 2. * L3)**2) / (144. * L3**2 * (L1 - L3)**2) * \
             (L3 * (L1 + 2. * L3) + L1 * (L1 - 4. * L3) * alpha)
 
-    # Resolve possible sigularity a==b and a==c
+    # Resolve possible singularity a==b and a==c
     cond3 = np.logical_and(cond0, np.logical_and(abs(b - c) < b * er,
                                                  abs(a - b) < b * er))
     if np.sum(cond3) != 0:
@@ -794,7 +794,7 @@ def _G1m(a, b, c):
     # Only computes G1 in voxels that have all eigenvalues larger than zero
     cond0 = _positive_evals(a, b, c)
 
-    # Apply formula for non problematic plaussible cases, i.e. b!=c
+    # Apply formula for non problematic plausible cases, i.e. b!=c
     cond1 = np.logical_and(cond0, (abs(b - c) > er))
     if np.sum(cond1) != 0:
         L1 = a[cond1]
@@ -804,7 +804,7 @@ def _G1m(a, b, c):
             (L1 + L2 + L3)**2 / (18 * L2 * (L2 - L3)**2) * \
             (2. * L2 + (L3**2 - 3 * L2 * L3) / np.sqrt(L2 * L3))
 
-    # Resolve possible sigularity b==c
+    # Resolve possible singularity b==c
     cond2 = np.logical_and(cond0, abs(b - c) < er)
     if np.sum(cond2) != 0:
         L1 = a[cond2]
@@ -849,7 +849,7 @@ def _G2m(a, b, c):
            kurtosis imaging. Magn Reson Med. 65(3), 823-836
     """
     # Float error used to compare two floats, abs(l1 - l2) < er for l1 = l2
-    # Error is defined as five order of magnitude larger than system's epslon
+    # Error is defined as five order of magnitude larger than system's epsilon
     er = np.finfo(a.ravel()[0]).eps * 1e5
 
     # Initialize G2
@@ -858,7 +858,7 @@ def _G2m(a, b, c):
     # Only computes G2 in voxels that have all eigenvalues larger than zero
     cond0 = _positive_evals(a, b, c)
 
-    # Apply formula for non problematic plaussible cases, i.e. b!=c
+    # Apply formula for non problematic plausible cases, i.e. b!=c
     cond1 = np.logical_and(cond0, (abs(b - c) > er))
     if np.sum(cond1) != 0:
         L1 = a[cond1]
@@ -868,7 +868,7 @@ def _G2m(a, b, c):
             (L1 + L2 + L3)**2 / (3 * (L2 - L3)**2) * \
             ((L2 + L3) / np.sqrt(L2 * L3) - 2)
 
-    # Resolve possible sigularity b==c
+    # Resolve possible singularity b==c
     cond2 = np.logical_and(cond0, abs(b - c) < er)
     if np.sum(cond2) != 0:
         L1 = a[cond2]
@@ -1824,7 +1824,7 @@ def wls_fit_dki(design_matrix, data):
 
     tol = 1e-6
 
-    # preparing data and initializing parametres
+    # preparing data and initializing parameters
     data = np.asarray(data)
     data_flat = data.reshape((-1, data.shape[-1]))
     dki_params = np.empty((len(data_flat), 27))
diff --git a/dipy/reconst/dki_micro.py b/dipy/reconst/dki_micro.py
index 8ec7002093..a7d875e1e8 100644
--- a/dipy/reconst/dki_micro.py
+++ b/dipy/reconst/dki_micro.py
@@ -134,7 +134,7 @@ def diffusion_components(dki_params, sphere='repulsion100', awf=None,
     edt_all = np.zeros(shape + (6,))
     idt_all = np.zeros(shape + (6,))
 
-    # Generate matrix that converts apparant diffusion coefficients to tensors
+    # Generate matrix that converts apparent diffusion coefficients to tensors
     B = np.zeros((sphere.x.size, 6))
     B[:, 0] = sphere.x * sphere.x  # Bxx
     B[:, 1] = sphere.x * sphere.y * 2.  # Bxy
diff --git a/dipy/reconst/fwdti.py b/dipy/reconst/fwdti.py
index e694fbe454..20067bb44f 100644
--- a/dipy/reconst/fwdti.py
+++ b/dipy/reconst/fwdti.py
@@ -295,7 +295,7 @@ def wls_iter(design_matrix, sig, S0, Diso=3e-3, mdreg=2.7e-3,
             SA = SI - FS*S0*SFW.T
             # SA < 0 means that the signal components from the free water
             # component is larger than the total fiber. This cases are present
-            # for inapropriate large volume fractions (given the current S0
+            # for inappropriate large volume fractions (given the current S0
             # value estimated). To overcome this issue negative SA are replaced
             # by data's min positive signal.
             SA[SA <= 0] = min_signal
@@ -471,7 +471,7 @@ def _nls_err_func(tensor_elements, design_matrix, data, Diso=3e-3,
         w = 1/(sigma**2)
 
     elif weighting == 'gmm':
-        # We use the Geman McClure M-estimator to compute the weights on the
+        # We use the Geman-McClure M-estimator to compute the weights on the
         # residuals:
         C = 1.4826 * np.median(np.abs(residuals - np.median(residuals)))
         with warnings.catch_warnings():
diff --git a/dipy/reconst/ivim.py b/dipy/reconst/ivim.py
index dbbdf27769..7388cbc86e 100644
--- a/dipy/reconst/ivim.py
+++ b/dipy/reconst/ivim.py
@@ -319,12 +319,12 @@ def fit(self, data):
         -------
         IvimFit object
         """
-        # Get S0_prime and D - paramters assuming a single exponential decay
+        # Get S0_prime and D - parameters assuming a single exponential decay
         # for signals for bvals greater than `split_b_D`
         S0_prime, D = self.estimate_linear_fit(
             data, self.split_b_D, less_than=False)
 
-        # Get S0 and D_star_prime - paramters assuming a single exponential
+        # Get S0 and D_star_prime - parameters assuming a single exponential
         # decay for for signals for bvals greater than `split_b_S0`.
 
         S0, D_star_prime = self.estimate_linear_fit(data, self.split_b_S0,
@@ -739,7 +739,7 @@ def ivim_mix_cost_one(self, phi, signal):
                (2016).
 
         """
-        # moore-penrose
+        # Moore-Penrose
         phi_mp = np.dot(np.linalg.inv(np.dot(phi.T, phi)), phi.T)
         f = np.dot(phi_mp, signal)
         yhat = np.dot(phi, f)  # - sigma
diff --git a/dipy/reconst/mcsd.py b/dipy/reconst/mcsd.py
index 46d6044ae5..f104d8d92c 100644
--- a/dipy/reconst/mcsd.py
+++ b/dipy/reconst/mcsd.py
@@ -165,7 +165,7 @@ def __init__(self, gtab, response, reg_sphere=default_sphere, iso=2):
         References
         ----------
         .. [1] Jeurissen, B., et al. NeuroImage 2014. Multi-tissue constrained
-               spherical deconvolution for improved analysisof multi-shell
+               spherical deconvolution for improved analysis of multi-shell
                diffusion MRI data
         .. [2] Tournier, J.D., et al. NeuroImage 2007. Robust determination of
                the fibre orientation distribution in diffusion MRI:
diff --git a/dipy/reconst/tests/test_dki.py b/dipy/reconst/tests/test_dki.py
index 17a459088d..60face5490 100644
--- a/dipy/reconst/tests/test_dki.py
+++ b/dipy/reconst/tests/test_dki.py
@@ -47,10 +47,10 @@
                                evecs_cross[2], kt_cross), axis=0)
 
 # Simulation 2. Spherical kurtosis tensor.- for white matter, this can be a
-# biological implaussible scenario, however this simulation is usefull for
+# biological implausible scenario, however this simulation is useful for
 # testing the estimation of directional apparent kurtosis and the mean
 # kurtosis, since its directional and mean kurtosis ground truth are a constant
-# which can be easly mathematicaly calculated.
+# which can be calculated easily mathematically.
 Di = 0.00099
 De = 0.00226
 mevals_sph = np.array([[Di, Di, Di], [De, De, De]])
@@ -69,7 +69,7 @@
 
 # Simulation 3. Multi-voxel simulations - dataset of four voxels is simulated.
 # Since the objective of this simulation is to see if procedures are able to
-# work with multi-dimentional data all voxels contains the same crossing signal
+# work with multi-dimensional data all voxels contains the same crossing signal
 # produced in simulation 1.
 
 DWI = np.zeros((2, 2, 1, len(gtab_2s.bvals)))
@@ -182,7 +182,7 @@ def test_carlson_rf():
     y = np.array([[2.0, 1.0], [3.0, 3.0]])
     z = np.array([[0.0, 0.0], [4.0, 4.0]])
 
-    # Defene reference outputs
+    # Define reference outputs
     RF_ref = np.array([[1.3110287771461, 1.8540746773014],
                        [0.58408284167715, 0.58408284167715]])
 
@@ -197,7 +197,7 @@ def test_carlson_rf():
     y = np.array([-1j, 1j, -1j, 1j])
     z = np.array([0.0, 0.0, 2, 1 - 1j])
 
-    # Defene reference outputs
+    # Define reference outputs
     RF_ref = np.array([1.8540746773014, 0.79612586584234 - 1.2138566698365j,
                        1.0441445654064, 0.93912050218619 - 0.53296252018635j])
     # Compute integrals
@@ -312,7 +312,7 @@ def test_Wrotate_crossing_fibers():
 
 def test_Wcons():
 
-    # Construct the 4D kurtosis tensor manualy from the crossing fiber kt
+    # Construct the 4D kurtosis tensor manually from the crossing fiber kt
     # simulate
     Wfit = np.zeros([3, 3, 3, 3])
 
@@ -528,10 +528,10 @@ def test_MK_singularities():
 
         # test singularity L1 == L3 and L1 != L2
         # since L1 is defined as the larger eigenvalue and L3 the smallest
-        # eigenvalue, this singularity teoretically will never be called,
+        # eigenvalue, this singularity theoretically will never be called,
         # because for L1 == L3, L2 have also to be  = L1 and L2.
         # Nevertheless, I decided to include this test since this singularity
-        # is revelant for cases that eigenvalues are not ordered
+        # is relevant for cases that eigenvalues are not ordered
 
         # artificially revert the eigenvalue and eigenvector order
         dki_params = dkiF.model_params.copy()
@@ -584,7 +584,7 @@ def test_dki_errors():
 
 def test_kurtosis_maximum():
     # TEST 1
-    # simulate a crossing fibers interserting at 70 degrees. The first fiber
+    # simulate a crossing fibers intersecting at 70 degrees. The first fiber
     # is aligned to the x-axis while the second fiber is aligned to the x-z
     # plane with an angular deviation of 70 degrees from the first one.
     # According to Neto Henriques et al, 2015 (NeuroImage 111: 85-99), the
diff --git a/dipy/reconst/tests/test_dki_micro.py b/dipy/reconst/tests/test_dki_micro.py
index bdb08ec60f..64173f36ed 100644
--- a/dipy/reconst/tests/test_dki_micro.py
+++ b/dipy/reconst/tests/test_dki_micro.py
@@ -43,14 +43,14 @@
 # approximation components larger than the fourth order. Thus parameter
 # estimates are only equal to the ground truth values of the simulation
 # if signals taylor components larger than the fourth order are removed.
-# Signal whithout this taylor components can be generated using the
+# Signal without this taylor components can be generated using the
 # multi_tensor_dki simulations. Therefore we used this function to test the
 # expected estimates of the model.
 
 DWIsim_all_taylor = np.zeros((2, 2, 2, gtab_2s.bvals.size))
 
 # Signal with all taylor components can be simulated using the function
-# multi_tensor. Generating this signals will be usefull to test the prediction
+# multi_tensor. Generating this signals will be useful to test the prediction
 # procedures of DKI-based microstructural model.
 
 
diff --git a/dipy/reconst/tests/test_dti.py b/dipy/reconst/tests/test_dti.py
index a6cda62180..6829dda73e 100644
--- a/dipy/reconst/tests/test_dti.py
+++ b/dipy/reconst/tests/test_dti.py
@@ -345,7 +345,7 @@ def test_wls_and_ls_fit():
     npt.assert_almost_equal(Y[0], b0)
     Y.shape = (-1,) + Y.shape
 
-    # Testing WLS Fit on Single Voxel
+    # Testing WLS Fit on single voxel
     # If you do something wonky (passing min_signal<0), you should get an
     # error:
     npt.assert_raises(ValueError, TensorModel, gtab, fit_method='WLS',
diff --git a/dipy/reconst/tests/test_fwdti.py b/dipy/reconst/tests/test_fwdti.py
index f39ee57571..558a7b5758 100644
--- a/dipy/reconst/tests/test_fwdti.py
+++ b/dipy/reconst/tests/test_fwdti.py
@@ -142,7 +142,7 @@ def test_fwdti_multi_voxel():
     assert_almost_equal(Ffwe, GTF)
     assert_almost_equal(MDfwe, MDref)
 
-    # Test cholesky
+    # Test Cholesky
     fwdm = fwdti.FreeWaterTensorModel(gtab_2s, 'NLS', cholesky=True)
     fwefit = fwdm.fit(DWI)
     FAfwe = fwefit.fa
diff --git a/dipy/reconst/tests/test_msdki.py b/dipy/reconst/tests/test_msdki.py
index 07b9232cd7..c2eec17817 100644
--- a/dipy/reconst/tests/test_msdki.py
+++ b/dipy/reconst/tests/test_msdki.py
@@ -23,7 +23,7 @@
 gtab_3s = gradient_table(bvals_3s, bvecs_3s)
 
 # Simulation 1. Spherical kurtosis tensor - MSK and MSD from the MSDKI model
-# should be equa to the MK and MD of the DKI tensor for cases of
+# should be equal to the MK and MD of the DKI tensor for cases of
 # spherical kurtosis tensors
 Di = 0.00099
 De = 0.00226
@@ -124,7 +124,7 @@ def test_errors():
     # fourth error raises if an given index point to more dimensions that data
     # does not contain
 
-    # define auxiliar function for the assert raises
+    # define auxiliary function for the assert raises
     def aux_test_fun(ob, ind):
         met = ob[ind].msk
         return met
diff --git a/dipy/reconst/tests/test_qtdmri.py b/dipy/reconst/tests/test_qtdmri.py
index 6f29f709cb..dfce6a58fe 100644
--- a/dipy/reconst/tests/test_qtdmri.py
+++ b/dipy/reconst/tests/test_qtdmri.py
@@ -158,7 +158,7 @@ def test_normalization_time():
 
 
 def test_anisotropic_isotropic_equivalence(radial_order=4, time_order=2):
-    # generate qt-scheme and arbitary synthetic crossing data.
+    # generate qt-scheme and arbitrary synthetic crossing data.
     gtab_4d = generate_gtab4D()
     l1, l2, l3 = [0.0015, 0.0003, 0.0003]
     S = generate_signal_crossing(gtab_4d, l1, l2, l3)
@@ -189,7 +189,7 @@ def test_anisotropic_isotropic_equivalence(radial_order=4, time_order=2):
     assert_array_almost_equal(pdf_aniso / pdf_aniso.max(),
                               pdf_iso / pdf_aniso.max())
 
-    # same norm of the laplacian
+    # same norm of the Laplacian
     norm_laplacian_aniso = qtdmri_fit_cart.norm_of_laplacian_signal()
     norm_laplacian_iso = qtdmri_fit_sphere.norm_of_laplacian_signal()
     assert_almost_equal(norm_laplacian_aniso / norm_laplacian_aniso,
@@ -402,7 +402,7 @@ def test_q0_constraint_and_unity_of_ODFs(radial_order=6, time_order=2):
     assert_almost_equal(float(E_q0_first_tau), 1.)
     assert_almost_equal(float(E_q0_last_tau), 1.)
 
-    # test if maginal ODF integral in sh is equal to one
+    # test if marginal ODF integral in sh is equal to one
     # Integral of Y00 spherical harmonic is 1 / (2 * np.sqrt(np.pi))
     # division with this results in normalization
     odf_sh = qtdmri_fit_lap.odf_sh(s=0, tau=tau.max())
diff --git a/dipy/reconst/tests/test_reco_utils.py b/dipy/reconst/tests/test_reco_utils.py
index 776882e552..a38c2e63b4 100644
--- a/dipy/reconst/tests/test_reco_utils.py
+++ b/dipy/reconst/tests/test_reco_utils.py
@@ -27,7 +27,7 @@ def test_argmax_from_countarrs():
     vertinds = np.arange(10, dtype=np.uint32)
     adj_counts = np.ones((10,), dtype=np.uint32)
     adj_inds_raw = np.arange(10, dtype=np.uint32)[::-1]
-    # when contigous - OK
+    # when contiguous - OK
     adj_inds = adj_inds_raw.copy()
     argmax_from_countarrs(vals, vertinds, adj_counts, adj_inds)
     # yield assert_array_equal(inds, [5, 6, 7, 8, 9])
diff --git a/dipy/segment/clustering.py b/dipy/segment/clustering.py
index c27e4ee5dc..adedf1ac6e 100644
--- a/dipy/segment/clustering.py
+++ b/dipy/segment/clustering.py
@@ -443,7 +443,7 @@ class QuickBundles(Clustering):
     >>> from nibabel import trackvis as tv
     >>> streams, hdr = tv.read(get_fnames('fornix'))
     >>> streamlines = [i[0] for i in streams]
-    >>> # Segment fornix with a treshold of 10mm and streamlines resampled
+    >>> # Segment fornix with a threshold of 10mm and streamlines resampled
     >>> # to 12 points.
     >>> qb = QuickBundles(threshold=10.)
     >>> clusters = qb.cluster(streamlines)
diff --git a/dipy/segment/clustering_algorithms.pyx b/dipy/segment/clustering_algorithms.pyx
index a742d6018a..e1f943af54 100644
--- a/dipy/segment/clustering_algorithms.pyx
+++ b/dipy/segment/clustering_algorithms.pyx
@@ -112,7 +112,7 @@ def quickbundles(streamlines, Metric metric, double threshold,
         if not streamline.flags.writeable or streamline.dtype != DTYPE:
             streamline = streamline.astype(DTYPE)
         cluster_id = qb.assignment_step(streamline, idx)
-        # The update step is performed right after the assignement step instead
+        # The update step is performed right after the assignment step instead
         # of after all streamlines have been assigned like k-means algorithm.
         qb.update_step(cluster_id)
 
diff --git a/dipy/segment/tests/test_quickbundles.py b/dipy/segment/tests/test_quickbundles.py
index 54448abdad..852cc434c4 100644
--- a/dipy/segment/tests/test_quickbundles.py
+++ b/dipy/segment/tests/test_quickbundles.py
@@ -86,7 +86,7 @@ def test_quickbundles_2D():
     # plt.plot(*zip(*data[10:, 0]), linestyle='None', marker='*')
     # plt.show()
 
-    # Theorically using a threshold above the following value will not
+    # Theoretically, using a threshold above the following value will not
     # produce expected results.
     threshold = np.sqrt(2*(10**2))-np.sqrt(2)
     metric = dipymetric.SumPointwiseEuclideanMetric()
diff --git a/dipy/sims/tests/test_voxel.py b/dipy/sims/tests/test_voxel.py
index fd2b3baa4b..0854d79764 100644
--- a/dipy/sims/tests/test_voxel.py
+++ b/dipy/sims/tests/test_voxel.py
@@ -27,7 +27,7 @@ def setup_module():
     gtab_2s = gradient_table(bvals_2s, bvecs_2s)
 
 
-# Unused with missing refernces to basis
+# Unused with missing references to basis
 # def diff2eigenvectors(dx, dy, dz):
 #     """ numerical derivatives 2 eigenvectors
 #     """
@@ -214,7 +214,7 @@ def test_kurtosis_elements():
                     key = (i+1) * (j+1) * (k+1) * (l+1)
                     assert_almost_equal(kurtosis_element(mD, frac, i, k, j, l),
                                         kt_ref[key])
-                    # Testing optional funtion inputs
+                    # Testing optional function inputs
                     assert_almost_equal(kurtosis_element(mD, frac, i, k, j, l),
                                         kurtosis_element(mD, frac, i, k, j, l,
                                                          D, MD))
diff --git a/dipy/stats/analysis.py b/dipy/stats/analysis.py
index 019f7152cb..412fcf581c 100644
--- a/dipy/stats/analysis.py
+++ b/dipy/stats/analysis.py
@@ -310,7 +310,7 @@ def gaussian_weights(bundle, n_points=100, return_mahalnobis=False,
         # This is a 3-by-3 array:
         node_coords = bundle.data[node::n_points]
         c = np.cov(node_coords.T, ddof=0)
-        # Reorganize as an upper diagonal matrix for expected Mahalnobis input:
+        # Reorganize as an upper diagonal matrix for expected Mahalanobis input:
         c = np.array([[c[0, 0], c[0, 1], c[0, 2]],
                       [0, c[1, 1], c[1, 2]],
                       [0, 0, c[2, 2]]])
@@ -321,7 +321,7 @@ def gaussian_weights(bundle, n_points=100, return_mahalnobis=False,
         for fn in range(len(bundle)):
             # In the special case where all the streamlines have the exact same
             # coordinate in this node, the covariance matrix is all zeros, so
-            # we can't calculate the Mahalnobis distance, we will instead give
+            # we can't calculate the Mahalanobis distance, we will instead give
             # each streamline an identical weight, equal to the number of
             # streamlines:
             if np.allclose(c, 0):
diff --git a/dipy/stats/tests/test_analysis.py b/dipy/stats/tests/test_analysis.py
index 6c604f8a5d..1597f6918b 100644
--- a/dipy/stats/tests/test_analysis.py
+++ b/dipy/stats/tests/test_analysis.py
@@ -77,7 +77,7 @@ def test_gaussian_weights():
     w = gaussian_weights(bundle, n_points=10)
     npt.assert_almost_equal(w, np.ones((len(bundle), 10)) * 0.5)
 
-    # Test when asked to return Mahalnobis, instead of weights
+    # Test when asked to return Mahalanobis, instead of weights
     w = gaussian_weights(bundle, n_points=10, return_mahalnobis=True)
     npt.assert_almost_equal(w, np.ones((len(bundle), 10)))
 
diff --git a/dipy/tracking/local/localtrack.pyx b/dipy/tracking/local/localtrack.pyx
index 5c98514ba5..365ad4d49b 100644
--- a/dipy/tracking/local/localtrack.pyx
+++ b/dipy/tracking/local/localtrack.pyx
@@ -455,7 +455,7 @@ cdef _pft(np.float_t[:, :] streamline,
 
             # Resample the particles if the weights are too uneven.
             # Particles with negligible weights are replaced by duplicates of
-            # those with high weigths through resampling
+            # those with high weights through resampling
             N_effective = 1. / sum_squared
             if N_effective < particle_count / 10.:
                 # copy data in the temp arrays
diff --git a/dipy/tracking/local/tests/test_tissue_classifier.py b/dipy/tracking/local/tests/test_tissue_classifier.py
index 14400fa71e..97715ae6b8 100644
--- a/dipy/tracking/local/tests/test_tissue_classifier.py
+++ b/dipy/tracking/local/tests/test_tissue_classifier.py
@@ -173,7 +173,7 @@ def test_cmc_tissue_classifier():
                                                    step_size=1,
                                                    average_voxel_size=1)
 
-    # Test contructors
+    # Test constructors
     for idx in np.ndindex(wm.shape):
         idx = np.asarray(idx, dtype="float64")
         npt.assert_almost_equal(cmc_tc.get_include(idx),
diff --git a/dipy/tracking/local/tests/test_tracking.py b/dipy/tracking/local/tests/test_tracking.py
index 5b2a9dd5b8..b29a6e0b13 100644
--- a/dipy/tracking/local/tests/test_tracking.py
+++ b/dipy/tracking/local/tests/test_tracking.py
@@ -769,7 +769,7 @@ def test_affine_transformations():
     # TST - combined affines
     a5 = a1 + a2 + a3
     a5[3, 3] = 1
-    # TST - in vivo affine exemple
+    # TST - in vivo affine example
     # Sometimes data have affines with tiny shear components.
     # For example, the small_101D data-set has some of that:
     fdata, _, _ = get_fnames('small_101D')
@@ -780,7 +780,7 @@ def test_affine_transformations():
         offset = affine[:3, 3]
         seeds_trans = [np.dot(lin, s) + offset for s in seeds]
 
-        # We compute the voxel size to ajust the step size to one voxel
+        # We compute the voxel size to adjust the step size to one voxel
         voxel_size = np.mean(np.sqrt(np.dot(lin, lin).diagonal()))
 
         streamlines = LocalTracking(direction_getter=dg,
diff --git a/dipy/tracking/propspeed.pyx b/dipy/tracking/propspeed.pyx
index 9eb9e74b44..da0bc50b9d 100644
--- a/dipy/tracking/propspeed.pyx
+++ b/dipy/tracking/propspeed.pyx
@@ -184,7 +184,7 @@ cdef void _trilinear_interpolation_iso(double *X,
         d[i] = X[i] - Xf[i]
         nd[i] = 1 - d[i]
     # weights
-    # the weights are actualy the volumes of the 8 smaller boxes that define
+    # the weights are actually the volumes of the 8 smaller boxes that define
     # the initial rectangular box for more on trilinear have a look here
     # http://en.wikipedia.org/wiki/Trilinear_interpolation
     # http://local.wasp.uwa.edu.au/~pbourke/miscellaneous/interpolation/index.html
@@ -385,7 +385,7 @@ cdef cnp.npy_intp _initial_direction(double* seed,double *qa,
     for i from 0 <= i < 3:
         point[i] = <cnp.npy_intp>floor(seed[i] + .5)
     point[3] = ref
-    # Find the offcet in memory to access the qa value
+    # Find the offset in memory to access the qa value
     off = offset(<cnp.npy_intp*>point,strides, 4, 8)
     qa_tmp = qa[off]
     # Check for scalar threshold
diff --git a/dipy/tracking/tests/test_streamline.py b/dipy/tracking/tests/test_streamline.py
index e1a5ac1473..8b722b8df0 100644
--- a/dipy/tracking/tests/test_streamline.py
+++ b/dipy/tracking/tests/test_streamline.py
@@ -556,7 +556,7 @@ def test_deform_streamlines():
     # Put orig_streamlines_world into voxmm
     orig_streamlines = transform_streamlines(orig_streamlines_world,
                                              np.linalg.inv(stream2world))
-    # All close because of floating pt inprecision
+    # All close because of floating pt imprecision
     for o, s in zip(orig_streamlines, streamlines):
         assert_allclose(s, o, rtol=1e-10, atol=0)
 
@@ -644,7 +644,7 @@ def dist_to_line(prev, next, curr):
 
 def test_compress_streamlines():
     for compress_func in [compress_streamlines_python, compress_streamlines]:
-        # Small streamlines (less than two points) are uncompressable.
+        # Small streamlines (less than two points) are incompressible.
         for small_streamline in [np.array([[]]),
                                  np.array([[1, 1, 1]]),
                                  np.array([[1, 1, 1], [2, 2, 2]])]:
@@ -682,7 +682,7 @@ def test_compress_streamlines():
         # (like the C++ version)
         compress_func(streamline, max_segment_length=np.inf)
 
-        # Uncompressable streamline when `tol_error` == 1.
+        # Incompressable streamline when `tol_error` == 1.
         simple_streamline = np.array([[0, 0, 0],
                                       [1, 1, 0],
                                       [1.5, np.inf, 0],
@@ -696,7 +696,7 @@ def test_compress_streamlines():
             assert_array_equal(c_streamline, simple_streamline)
 
     # Create a special streamline where every other point is increasingly
-    # farther from a straigth line formed by the streamline endpoints.
+    # farther from a straight line formed by the streamline endpoints.
     tol_errors = np.linspace(0, 10, 21)
     orthogonal_line = np.array([[-np.sqrt(2)/2, np.sqrt(2)/2, 0]],
                                dtype=np.float32)
diff --git a/dipy/tracking/utils.py b/dipy/tracking/utils.py
index 9bde258ffc..b6924030f4 100644
--- a/dipy/tracking/utils.py
+++ b/dipy/tracking/utils.py
@@ -741,7 +741,7 @@ def near_roi(streamlines, region_of_interest, affine=None, tol=None,
     roi_coords = np.array(np.where(region_of_interest)).T
     x_roi_coords = apply_affine(affine, roi_coords)
 
-    # If it's already a list, we can save time by preallocating the output
+    # If it's already a list, we can save time by pre-allocating the output
     if isinstance(streamlines, list):
         out = np.zeros(len(streamlines), dtype=bool)
         for ii, sl in enumerate(streamlines):
diff --git a/dipy/tracking/vox2track.pyx b/dipy/tracking/vox2track.pyx
index ddb2207da5..09d1590a5b 100644
--- a/dipy/tracking/vox2track.pyx
+++ b/dipy/tracking/vox2track.pyx
@@ -144,7 +144,7 @@ def streamline_mapping(streamlines, voxel_size=None, affine=None,
                      voxel_indices[j, 2])
             uniq_points.add(point)
 
-        # Add the index of this streamline for each uniq voxel
+        # Add the index of this streamline for each unique voxel
         for point in uniq_points:
             if point in mapping:
                 mapping[point].append(i)
diff --git a/dipy/viz/projections.py b/dipy/viz/projections.py
index 6c087c255c..41b16f4966 100644
--- a/dipy/viz/projections.py
+++ b/dipy/viz/projections.py
@@ -82,7 +82,7 @@ def sph_project(vertices, val, ax=None, vmin=None, vmax=None, cmap=None,
     # positive:
     neg_idx = np.where(verts_rot[0] > 0)
 
-    # rotate the entire bvector around to point in the other direction:
+    # rotate the entire b-vector around to point in the other direction:
     verts_rot[:, neg_idx] *= -1
 
     _, theta, phi = geo.cart2sphere(verts_rot[0], verts_rot[1], verts_rot[2])
@@ -109,7 +109,7 @@ def sph_project(vertices, val, ax=None, vmin=None, vmax=None, cmap=None,
 
         r = (val - my_min) / float(my_max - my_min)
 
-        # Enforce the maximum and minumum boundaries, if there are values
+        # Enforce the maximum and minimum boundaries, if there are values
         # outside those boundaries:
         r[r < 0] = 0
         r[r > 1] = 1
diff --git a/dipy/viz/tests/test_regtools.py b/dipy/viz/tests/test_regtools.py
index ddfd07bc50..e81e2fcb8b 100644
--- a/dipy/viz/tests/test_regtools.py
+++ b/dipy/viz/tests/test_regtools.py
@@ -26,7 +26,7 @@ def test_plot_2d_diffeomorphic_map():
     mapping = sdr.optimize(static, moving)
     # Smoke testing of plots
     ff = regtools.plot_2d_diffeomorphic_map(mapping, 10)
-    # Defualt shape is static shape, moving shape
+    # Default shape is static shape, moving shape
     npt.assert_equal(ff[0].shape, st_shape)
     npt.assert_equal(ff[1].shape, mv_shape)
     # Can specify shape
diff --git a/dipy/workflows/align.py b/dipy/workflows/align.py
index c29cf7c08d..cbfbfbba58 100644
--- a/dipy/workflows/align.py
+++ b/dipy/workflows/align.py
@@ -178,7 +178,7 @@ def run(self, static_files, moving_files,
 
         .. [Garyfallidis17] Garyfallidis et al. Recognition of white matter
         bundles using local and global streamline-based registration
-        and clustering, Neuroimage, 2017.
+        and clustering, NeuroImage, 2017.
         """
         io_it = self.get_io_iterator()
 
@@ -855,7 +855,7 @@ def run(self, static_image_files, moving_image_files, prealign_file='',
             raise ValueError("Invalid similarity metric: Please"
                              " provide a valid metric like 'ssd', 'cc', 'em'")
 
-        logging.info("Starting Diffeormorphic Registration")
+        logging.info("Starting Diffeomorphic Registration")
         logging.info('Using {0} Metric'.format(metric.upper()))
 
         # Init parameter if they are not setup
@@ -928,5 +928,5 @@ def run(self, static_image_files, moving_image_files, prealign_file='',
             # Saving
             logging.info('Saving warped {0}'.format(owarped_file))
             save_nifti(owarped_file, warped_moving, static_grid2world)
-            logging.info('Saving Diffeormorphic map {0}'.format(omap_file))
+            logging.info('Saving Diffeomorphic map {0}'.format(omap_file))
             save_nifti(omap_file, mapping_data, mapping.codomain_world2grid)
diff --git a/dipy/workflows/denoise.py b/dipy/workflows/denoise.py
index c6af05cf25..5f2ad6c4bf 100644
--- a/dipy/workflows/denoise.py
+++ b/dipy/workflows/denoise.py
@@ -33,7 +33,7 @@ def run(self, input_files, sigma=0, out_dir='',
         out_dir : string, optional
             Output directory (default input file directory)
         out_denoised : string, optional
-            Name of the resuting denoised volume (default: dwi_nlmeans.nii.gz)
+            Name of the resulting denoised volume (default: dwi_nlmeans.nii.gz)
         """
         io_it = self.get_io_iterator()
         for fpath, odenoised in io_it:
diff --git a/dipy/workflows/flow_runner.py b/dipy/workflows/flow_runner.py
index 52e08511a6..599e82e3ec 100644
--- a/dipy/workflows/flow_runner.py
+++ b/dipy/workflows/flow_runner.py
@@ -12,7 +12,7 @@
 
 
 def get_level(lvl):
-    """ Transforms the loggin level passed on the commandline into a proper
+    """ Transforms the logging level passed on the commandline into a proper
     logging level name.
     """
     try:
@@ -47,7 +47,7 @@ def run_flow(flow):
                         help='Prepend mixed input names to output names.')
 
     # Add logging parameters common to all workflows
-    msg = 'Log messsages display level. Accepted options include CRITICAL,'
+    msg = 'Log messages display level. Accepted options include CRITICAL,'
     msg += ' ERROR, WARNING, INFO, DEBUG and NOTSET (default INFO).'
     parser.add_argument('--log_level', action='store', dest='log_level',
                         metavar='string', required=False, default='INFO',
diff --git a/dipy/workflows/io.py b/dipy/workflows/io.py
index 822104efc8..ed8a546ca4 100644
--- a/dipy/workflows/io.py
+++ b/dipy/workflows/io.py
@@ -71,8 +71,8 @@ def run(self, input_files,
 
             if os.path.basename(input_path).lower().find('bval') > -1:
                 bvals = np.loadtxt(input_path)
-                logging.info('Bvalues \n{0}'.format(bvals))
-                logging.info('Total number of bvalues {}'.format(len(bvals)))
+                logging.info('b-values \n{0}'.format(bvals))
+                logging.info('Total number of b-values {}'.format(len(bvals)))
                 shells = np.sum(np.diff(np.sort(bvals)) > bshell_thr)
                 logging.info('Number of gradient shells {0}'.format(shells))
                 logging.info('Number of b0s {0} (b0_thr {1})\n'
diff --git a/dipy/workflows/reconst.py b/dipy/workflows/reconst.py
index ee544eff70..2655007100 100644
--- a/dipy/workflows/reconst.py
+++ b/dipy/workflows/reconst.py
@@ -50,7 +50,7 @@ def run(self, data_files, bvals_files, bvecs_files, small_delta, big_delta,
         files to an output directory specified by `out_dir`.
 
         In order for the MAPMRI workflow to work in the way
-        intended either the laplacian or positivity or both must
+        intended either the Laplacian or positivity or both must
         be set to True.
 
         Parameters
@@ -86,7 +86,7 @@ def run(self, data_files, bvals_files, bvecs_files, small_delta, big_delta,
             ng, perng, parng
             (default: [] (all))
         laplacian_weighting : float, optional
-            Weighting value used in fitting the MAPMRI model in the laplacian
+            Weighting value used in fitting the MAPMRI model in the Laplacian
             and both model types. (default: 0.05)
         radial_order : unsigned int, optional
             Even value used to set the order of the basis
@@ -96,7 +96,7 @@ def run(self, data_files, bvals_files, bvecs_files, small_delta, big_delta,
         out_rtop : string, optional
             Name of the rtop to be saved
         out_lapnorm : string, optional
-            Name of the norm of laplacian signal to be saved
+            Name of the norm of Laplacian signal to be saved
         out_msd : string, optional
             Name of the msd to be saved
         out_qiv : string, optional
@@ -430,7 +430,7 @@ def run(self, input_files, bvalues_files, bvectors_files, mask_files,
         frf : variable float, optional
             Fiber response function can be for example inputed as 15 4 4
             (from the command line) or [15, 4, 4] from a Python script to be
-            converted to float and mutiplied by 10**-4 . If None
+            converted to float and multiplied by 10**-4 . If None
             the fiber response function will be computed automatically
             (default: None).
         extract_pam_values : bool, optional
diff --git a/dipy/workflows/tests/test_tracking.py b/dipy/workflows/tests/test_tracking.py
index 4da7bc18f4..95f3c5d6ba 100644
--- a/dipy/workflows/tests/test_tracking.py
+++ b/dipy/workflows/tests/test_tracking.py
@@ -14,7 +14,7 @@
                                      PFTrackingPAMFlow)
 
 
-def test_particule_filtering_traking_workflows():
+def test_particle_filtering_traking_workflows():
     with TemporaryDirectory() as out_dir:
         dwi_path, bval_path, bvec_path = get_fnames('small_64D')
         vol_img = nib.load(dwi_path)
@@ -170,7 +170,7 @@ def test_local_fiber_tracking_workflow():
             lf_track_pam.last_generated_outputs['out_tractogram']
         assert_false(is_tractogram_empty(tractogram_path))
 
-        # Test tracking with pam with sh and closestpeaks getter
+        # Test tracking with pam with sh and closest peaks getter
         lf_track_pam = LocalFiberTrackingPAMFlow()
         lf_track_pam._force_overwrite = True
         lf_track_pam.run(pam_path, gfa_path, seeds_path,
@@ -223,4 +223,4 @@ def seeds_are_same_space_as_streamlines(tractogram_path):
 
 if __name__ == '__main__':
     test_local_fiber_tracking_workflow()
-    test_particule_filtering_traking_workflows()
+    test_particle_filtering_traking_workflows()
diff --git a/dipy/workflows/workflow.py b/dipy/workflows/workflow.py
index 6afbcffbad..da4aab11e9 100644
--- a/dipy/workflows/workflow.py
+++ b/dipy/workflows/workflow.py
@@ -89,7 +89,7 @@ def run(self, *args, **kwargs):
         """Execute the workflow.
 
         Since this is an abstract class, raise exception if this code is
-        reached (not impletemented in child class or literally called on this
+        reached (not implemented in child class or literally called on this
         class)
         """
         raise Exception('Error: {} does not have a run method.'.
diff --git a/doc/examples/reconst_qtdmri.py b/doc/examples/reconst_qtdmri.py
index 267608c941..067c263820 100644
--- a/doc/examples/reconst_qtdmri.py
+++ b/doc/examples/reconst_qtdmri.py
@@ -407,7 +407,7 @@ def plot_mean_with_std(ax, time, ind1, plotcolor, ls='-', std_mult=1,
 also allows for the estimation of time-dependent ODFs. Once the Qtdmri model
 is fitted it can be simply called by qtdmri_fit.odf(sphere,
 s=sharpening_factor). This is identical to how the mapmri module functions,
-and allows to study the time-dependence of ODF directionallity.
+and allows to study the time-dependence of ODF directionality.
 
 This concludes the example on qt-dMRI. As we showed, approaches such as qt-dMRI
 can help in studying the (finite-:math:`\tau`) temporal properties of diffusion
diff --git a/doc/examples/simulate_dki.py b/doc/examples/simulate_dki.py
index 435090d0f1..211d1ef6d4 100644
--- a/doc/examples/simulate_dki.py
+++ b/doc/examples/simulate_dki.py
@@ -36,7 +36,7 @@
 
 """
 DKI requires data from more than one non-zero b-value. Since the dataset
-``small_64D`` was acquired with one non-zero bvalue we artificialy produce a
+``small_64D`` was acquired with one non-zero b-value we artificially produce a
 second non-zero b-value.
 """
 
@@ -80,7 +80,7 @@
 of each fiber population and the water fraction of each different medium
 """
 
-fie = 0.49  # intra axonal water fraction
+fie = 0.49  # intra-axonal water fraction
 fractions = [fie*50, (1 - fie)*50, fie*50, (1 - fie)*50]
 
 """
diff --git a/doc/tools/docgen_cmd.py b/doc/tools/docgen_cmd.py
index c15f5f086c..6158167f47 100755
--- a/doc/tools/docgen_cmd.py
+++ b/doc/tools/docgen_cmd.py
@@ -117,7 +117,7 @@ def get_help_string(class_obj):
                       f.lower().startswith("dipy_")]
 
     workflow_desc = {}
-    # We get all workflows class obj in a dictionnary
+    # We get all workflows class obj in a dictionary
     for path_file in os.listdir(pjoin('..', 'dipy', 'workflows')):
         module_name = inspect.getmodulename(path_file)
         if module_name is None: