mzaradzki

fcn32model = fcn32_blank()
        
fcn32shape = fcn32model.layers[-1].output_shape
    
fcn32size = fcn32shape[2] # INFO: =32 when images are 512x512
    
sp4 = Convolution2D(21, 1, 1,
                    border_mode='same', # INFO : border_mode does not matter for 1x1
                    activation=None,
                    name='score_pool4')

mzaradzki

modelWRD = Sequential()

# 1st layer is a dummy-permutation=identity to specify input shape
modelWRD.add( Permute((1,), input_shape=(n_words,)) )

modelWRD.add( EMBEDDING )

modelWRD.add( Lambda(
                   lambda x : K.sum(x,axis=1), # sum over words

mzaradzki

if pretrained:
    EMBEDDING = Embedding(vocab_size,
                          embedding_dimension,
                          weights=[glove_embedding_matrix])
else:
    EMBEDDING = Embedding(vocab_size,
                          embedding_dimension)
    

mzaradzki

WARNING : Python 2.7 is much easier to run with Caffe than Python 3.5

• https://iqbalnaved.wordpress.com/2016/05/08/installing-caffe-and-pycaffe-on-ubuntu-14-04/ WARNING : Command line at step 2 is actually 2 lines WARNING : You dont have to use cmake for compiling, see berkeleyvision

• http://caffe.berkeleyvision.org/install_apt.html WARNING : you probably dont need all the dependencies, especially the "manual" ones

mzaradzki

exports.handler = (event, context, callback) => {
    
    // WARNING :
    // This snippet assumes : event.Records[0].eventName == 'ObjectCreated:Put'
    // but the ful code deals with both 'ObjectCreated:Put' and 'ObjectRemoved:Delete'
    
    var filename = event.Records[0].s3.object.key;
    var bucketname = event.Records[0].s3.bucket.name;
    
    var params = {

mzaradzki

addToIndex = function (bucketName, docName, docContent, context) {
    
    var csd = new AWS.CloudSearchDomain({
        endpoint: CS_NAME+'.'+SERVICES_REGION+'.cloudsearch.amazonaws.com',
        apiVersion: '2013-01-01'
    });
    
    // see documentation at :
    // http://docs.aws.amazon.com/cloudsearch/latest/developerguide/preparing-data.html#creating-document-batches
    var jbatch = [  {"type": "add",

mzaradzki

exports.handler = (event, context, callback) => {
  
    var csd = new AWS.CloudSearchDomain({
        endpoint: CS_NAME+'.'+SERVICES_REGION+'.cloudsearch.amazonaws.com',
        apiVersion: '2013-01-01'
    });
  
    var params = {
        query: event.query,
        sort: '_score desc',

mzaradzki

for col in categories:
    cs = dfX[col].value_counts(normalize=False, sort=True, ascending=False)
    rare_values = [k for k in cs.keys() if cs[k]<40] # Theshold = 40 occurrences
    if len(rare_values)>0:
        print( 'Trim values : ', col, len(rare_values))
        dfX.loc[dfX[col].isin(rare_values), col] = col+'_rare'

# Output :
# Trim values : funder      1730
# Trim values : installer   1982

mzaradzki

# Search for variables that are very similar
def show_similars(cols, threshold=0.90):
    for i1, col1 in enumerate(cols):
        for i2, col2 in enumerate(cols):
            if (i1<i2):
                cm12 = pd.crosstab(dfX[col1], dfX[col2]).values # contingency table
                cv12 = cramers_corrected_stat(cm12) # Cramer V statistic
                if (cv12 > threshold):
                    print((col1, col2), int(cv12*100))

mzaradzki

for col, tp in nullcols:
    if (tp == str):
        dfX.loc[dfX[col].isnull(), col] = 'MISSING'