def fill_unknown_traits(traits_to_update, new_traits):
"""Returns traits_to_update, with all None values replaced with the corresponding index in new_traits
traits_to_update -- a numpy array, with None values representing missing data
new_traits -- a numpy array, with None values representing missing data
returns an array that is traits_to_update, with all None values replaced with
the corresponding values in new_traits.
This is useful when some, but not all traits of an organism are known.
For example, PCR of specific genes may have fixed some traits, but you would
like to predict the rest.
Note -- in the special case where traits_to_update is the value None,
new_traits will be returned. This is done so that we don't have to guess
or specify beforehand how many traits there will be when filling in tip nodes
"""
if traits_to_update is None:
return array(new_traits)
masked_traits_to_update = masked_object(traits_to_update,None)
result = where(masked_traits_to_update.mask == True,\
new_traits,masked_traits_to_update)
return array(result)
def calc_mean_and_std(ROICorrMaps,
n_subjects,
ROIAtlasmask,
ddof=1,
applyFisher=False):
'''
Function for calculating the mean and standard
deviation of the data. At a time, only one of the nii
file is loaded and the elements keep on adding as we
enumerate over the subjects.
'''
mask = nib.load(ROIAtlasmask).get_data()
mask = ma.masked_object(mask, 0).mask
if (n_subjects != 0):
f = nib.load(ROICorrMaps[0])
dimensions = f.get_header().get_data_shape()
print(dimensions)
else:
exit
mask = np.repeat(mask[:, :, :, np.newaxis], dimensions[3], axis=3)
# print(ROICorrMaps)
Sample_mean_Array = np.zeros(dimensions)
Sample_std_Array = np.zeros(dimensions)
Sample_mean_Array = ma.masked_array(Sample_mean_Array,
mask=mask,
fill_value=0)
Sample_std_Array = ma.masked_array(Sample_std_Array,
mask=mask,
fill_value=0)
for count, subject in enumerate(ROICorrMaps):
Corr_data = nib.load(subject).get_data()
Corr_data = ma.masked_array(Corr_data, mask=mask, fill_value=0)
if applyFisher:
Corr_data = np.arctanh(Corr_data)
Sample_mean_Array += Corr_data
Sample_std_Array += np.square(Corr_data)
print('Done subject ', count + 1)
Sample_mean_Array /= n_subjects
# import pdb; pdb.set_trace()
Sample_std_Array = np.sqrt(
(Sample_std_Array - n_subjects * np.square(Sample_mean_Array)) /
(n_subjects - ddof))
return Sample_mean_Array, Sample_std_Array
import numpy as np import numpy.ma as ma food = np.array(['green_eggs', 'ham'], dtype=object) # don't eat spoiled food eat = ma.masked_object(food, 'green_eggs') print eat # plain ol` ham is boring fresh_food = np.array(['cheese', 'ham', 'pineapple'], dtype=object) eat = ma.masked_object(fresh_food, 'green_eggs') print eat eat
]
# - Use Pandas to read columns according to colnames
data = pandas.read_csv('Video_Game_Sales_as_of_Jan_2017.csv', names=colnames)
# - Converting columns into NumPy Arrays
name = np.asarray(data.Name.tolist())
platform = np.asarray(data.Platform.tolist())
year_of_release = np.asarray(data.Year_Of_Release.tolist())
genre = np.asarray(data.Genre.tolist())
publisher = np.asarray(data.Publisher.tolist())
# - Masking Critic Scores with review count less than 20
critic_score = np.asarray(data.Critic_Score.tolist())
critic_count = ma.masked_invalid(data.Critic_Count.tolist())
critic_count = ma.masked_less(critic_count, 20)
critic_score = ma.masked_object(critic_score, critic_count)
# - Masking User Scores with review count less than 20
user_score = np.asarray(data.User_Score.tolist()) * 10
user_count = ma.masked_invalid(data.User_Count.tolist())
user_count = ma.masked_less(user_count, 20)
user_score = ma.masked_object(user_score, user_count)
rating = np.asarray(data.Rating.tolist())
# ============================= Global Sales Code =============================
# - Masking Global Sales 3 STD away from medium
global_sales = np.asarray(data.Global_Sales.tolist()) # millions
global_sales_mean = sp.mean(global_sales)
global_sales_std = sp.std(global_sales)
global_sales = ma.masked_outside(global_sales,
2. masked_invalid(a[, copy]): Mask an array where invalid values occur (NaNs or infs)
3. masked_less(x, value[, copy]) Mask an array where less than a given value.
4. masked_less_equal(x, value[, copy]) Mask an array where less than or equal to a given value.
5. masked_not_equal(x, value[, copy]) Mask an array where not equal to a given value.
6. masked_outside(x, v1, v2[, copy]) Mask an array outside a given interval, excludng v1 and v2
'''
# 7. numpy.ma.masked_object
print("--------- Example 5: use of masked_object() ---------")
food = np.array(['green_eggs', 'ham'], dtype=object)
## it is required to specify type as object to perform masked_object
eat = ma.masked_object(food, "green_eggs")
print("result of masked_object is : ", eat)
'''
8. numpy.ma.masked_values(x, value, rtol=1e-05, atol=1e-08, copy=True, shrink=True)
Mask using floating point equality.
Return a MaskedArray, masked where the data in array x are approximately
equal to value.
9. masked_where(condition, a[, copy]) Mask an array where a condition is met.
'''
x = ma.array([1, 2, 3])
x[0] = ma.masked
print("*" * 50)
print("--------- Example 6: masking an entry ---------")
print("masked x is ", x)
x.mask = True