Python Dataset.get_ids_by_features方法代码示例

# 需要导入模块: from neurosynth.base.dataset import Dataset [as 别名]
# 或者: from neurosynth.base.dataset.Dataset import get_ids_by_features [as 别名]
def generate_maps(terms,output_dir):

    f,d = download_data()
    features = pandas.read_csv(f,sep="\t")  
    database = pandas.read_csv(d,sep="\t")  

    output_dir = "%s/maps" %(output_dir)

    print "Deriving pickled maps to extract relationships from..."
    dataset = Dataset(d)
    dataset.add_features(f)
    for t in range(len(terms)):
        term = terms[t]
        print "Generating P(term|activation) for term %s, %s of %s" %(term,t,len(terms))
        ids = dataset.get_ids_by_features(term)
        maps = meta.MetaAnalysis(dataset,ids)
        term_name = term.replace(" ","_")
        pickle.dump(maps.images["pFgA_z"],open("%s/%s_pFgA_z.pkl" %(output_dir,term_name),"wb"))

# 需要导入模块: from neurosynth.base.dataset import Dataset [as 别名]
# 或者: from neurosynth.base.dataset.Dataset import get_ids_by_features [as 别名]
def extract_relations(terms,maps_dir,output_dir):

    if isinstance(terms,str):
        terms = [terms]

    f,d = download_data()
    features = pandas.read_csv(f,sep="\t")  
    database = pandas.read_csv(d,sep="\t")  
    allterms = features.columns.tolist()
    allterms.pop(0)  #pmid

    dataset = Dataset(d)
    dataset.add_features(f)
    image_matrix = pandas.DataFrame(columns=range(228453))
    for t in range(len(allterms)):
        term = allterms[t]
        term_name = term.replace(" ","_")
        pickled_map = "%s/%s_pFgA_z.pkl" %(maps_dir,term_name)
        if not os.path.exists(pickled_map):
            print "Generating P(term|activation) for term %s" %(term)
            ids = dataset.get_ids_by_features(term)
            maps = meta.MetaAnalysis(dataset,ids)
            pickle.dump(maps.images["pFgA_z"],open(pickled_map,"wb"))
        map_data = pickle.load(open(pickled_map,"rb"))
        image_matrix.loc[term] = map_data

    sims = pandas.DataFrame(columns=image_matrix.index)
    tuples = []
    for t1 in range(len(terms)):
        term1 = terms[t1]
        print "Extracting NeuroSynth relationships for term %s..." %(term1)
        for t2 in range(len(terms)):
            term2 = terms[t2]
            if t1<t2:
                score = pearsonr(image_matrix.loc[term1],image_matrix.loc[term2])[0]
                tuples.append((term1,term2,score))

    save_relations(output_dir=output_dir,relations=tuples)

# 需要导入模块: from neurosynth.base.dataset import Dataset [as 别名]
# 或者: from neurosynth.base.dataset.Dataset import get_ids_by_features [as 别名]
from neurosynth.base.dataset import Dataset
from neurosynth.analysis import meta
import os
dataset = Dataset('database.txt')
dataset.add_features('features.txt')
print dataset.get_feature_names()
ids = dataset.get_ids_by_features('emo*', threshold=0.001)
print len(ids)
ma = meta.MetaAnalysis(dataset, ids)
ma.save_results('emotion')

# 需要导入模块: from neurosynth.base.dataset import Dataset [as 别名]
# 或者: from neurosynth.base.dataset.Dataset import get_ids_by_features [as 别名]
resource_dir = path.join(path.pardir, 'resources')

# make sure we have the data
dataset_dir = path.join(path.expanduser('~'), 'Documents', 'neurosynth-data')
database_path = path.join(dataset_dir, 'database_bregma.txt')
neurosynth_data_url = 'https://github.com/wmpauli/neurosynth-data'
if not path.exists(database_path):
    print("Please download dataset from %s and store it in %s" % (neurosynth_data_url, dataset_dir))

# load dataset, both image table and feature table
r = 1.0 # 1mm smoothing kernel
transform = {'BREGMA': transformations.bregma_to_whs()}
target = 'WHS'
masker_filename = path.join(resource_dir, 'WHS_SD_rat_brainmask_sm_v2.nii.gz')
dataset = Dataset(path.join(dataset_dir, 'database_bregma.txt'), masker=masker_filename, r=r, transform=transform, target=target)
dataset.feature_table = FeatureTable(dataset)
dataset.add_features(path.join(dataset_dir, "features_bregma.txt")) # add features
fn = dataset.get_feature_names()

# get the ids of studies where this feature occurs
ids = dataset.get_ids_by_features(('%s*' % feature), threshold=0.1)
ma = meta.MetaAnalysis(dataset, ids)
results_path = path.join('results', 'meta', feature)
if not path.exists(results_path):
    makedirs(results_path)

    print("saving results to: %s" % results_path)
ma.save_results(results_path)

# note, figure 2 of manuscript was used by plotting the z-score statistical maps for forward inference (pAgF_z.nii.gz) and reverse inference (pFgA_z.nii.gz)

# 需要导入模块: from neurosynth.base.dataset import Dataset [as 别名]
# 或者: from neurosynth.base.dataset.Dataset import get_ids_by_features [as 别名]
# Now that our Dataset has both activation data and some features, we're ready to start doing some analyses! By design, Neurosynth focuses on facilitating simple, fast, and modestly useful analyses. This means you probably won't break any new ground using Neurosynth, but you should be able to supplement results you've generated using other approaches with a bunch of nifty analyses that take just 2 - 3 lines of code.
# 
# ### Simple feature-based meta-analyses
# The most straightforward thing you can do with Neurosynth is use the features we just loaded above to perform automated large-scale meta-analyses of the literature. Let's see what features we have:

# <codecell>

dataset.get_feature_names()

# <markdowncell>

# If the loading process went smoothly, this should return a list of about 500 terms. We can use these terms--either in isolation or in combination--to select articles for inclusion in a meta-analysis. For example, suppose we want to run a meta-analysis of emotion studies. We could operationally define a study of emotion as one in which the authors used words starting with 'emo' with high frequency:

# <codecell>

ids = dataset.get_ids_by_features('emo*', threshold=0.001)

# <markdowncell>

# Here we're asking for a list of IDs of all studies that use words starting with 'emo' (e.g.,'emotion', 'emotional', 'emotionally', etc.) at a frequency of 1 in 1,000 words or greater (in other words, if an article has 5,000 words of text, it will only be included in our set if it uses words starting with 'emo' at least 5 times). Let's find out how many studies are in our list:

# <codecell>

len(ids)

# <markdowncell>

# The resulting set includes 639 studies.
# 
# Once we've got a set of studies we're happy with, we can run a simple meta-analysis, prefixing all output files with the string 'emotion' to distinguish them from other analyses we might run: