def initialize_directories(dock=None):
"""
Initialize directories for procedure's product files.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
raises:
returns:
(dict<str>): collection of paths to directories for procedure's files
"""
# Define paths to directories.
path_permutation = os.path.join(dock, "permutation")
path_genes = os.path.join(path_permutation, "genes")
# Remove previous files to avoid version or batch confusion.
utility.remove_directory(path=path_permutation)
# Initialize directories.
utility.create_directory(path_permutation)
utility.create_directory(path_genes)
# Collect information.
paths = dict()
paths["permutation"] = path_permutation
paths["genes"] = path_genes
# Return information.
return paths
def initialize_directories(
restore=None,
path_dock=None,
):
"""
Initialize directories for procedure's product files.
arguments:
restore (bool): whether to remove previous versions of data
path_dock (str): path to dock directory for source and product
directories and files
raises:
returns:
(dict<str>): collection of paths to directories for procedure's files
"""
# Collect paths.
paths = dict()
# Define paths to directories.
paths["dock"] = path_dock
paths["organization"] = os.path.join(path_dock, "organization")
paths["coombes_polygene"] = os.path.join(
path_dock, "coombes_prs_gems_gain_mayo_all_2020-10-13")
# Remove previous files to avoid version or batch confusion.
if restore:
utility.remove_directory(path=paths["organization"])
# Initialize directories.
utility.create_directories(path=paths["organization"])
# Return information.
return paths
def initialize_directories(dock=None):
"""
Initialize directories for procedure's product files.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
raises:
returns:
(dict<str>): collection of paths to directories for procedure's files
"""
# Collect paths.
paths = dict()
# Define paths to directories.
paths["dock"] = dock
paths["function"] = os.path.join(paths["dock"], "function")
# Remove previous files to avoid version or batch confusion.
utility.remove_directory(path=paths["function"])
utility.create_directory(path=paths["function"])
# Return information.
return paths
def copy_example_files():
examples_dir = posixpath.join(config.CODE_DIR, 'examples')
examples_destination = posixpath.join(config.RELEASE_DIR, 'driver', 'examples')
utility.remove_directory(examples_destination)
shutil.copytree(examples_dir, examples_destination, ignore=ignored_example_files)
stdbool_h_path = posixpath.join(examples_dir, 'stdbool.h')
shutil.copy2(stdbool_h_path, examples_destination)
def execute_procedure(dock=None, count=None):
"""
Function to execute module's main behavior.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
count (int): count of shuffles to create and store
raises:
returns:
"""
# Remove previous files to avoid version or batch confusion.
path_shuffle = os.path.join(dock, "shuffle")
utility.remove_directory(path=path_shuffle)
# Read source information from file.
source = read_source(dock=dock)
# Report.
utility.print_terminal_partition(level=3)
print(
"Creating " + str(count) + " shuffles for matrices of dimension " +
"zero: " + str(source["tissues_selection"]) + " by dimension one: " +
str(source["persons_selection"]) + ". "
"Notice that shuffles occur across dimension one (tissues for each " +
"person)."
)
print(
"Hence, values will stay matched to their respective tissues, but " +
"they will be shuffled with respect to persons."
)
utility.print_terminal_partition(level=3)
# Create shuffle indices.
shuffles = create_shuffle_indices(
count=count,
dimension_zero=source["tissues_selection"],
dimension_one=source["persons_selection"],
)
# Compile information.
information = {
"shuffles": shuffles
}
#Write product information to file.
write_product(dock=dock, information=information)
pass
def copy_example_files():
examples_dir = posixpath.join(config.CODE_DIR, 'examples')
examples_destination = posixpath.join(config.RELEASE_DIR, 'driver',
'examples')
utility.remove_directory(examples_destination)
shutil.copytree(examples_dir,
examples_destination,
ignore=ignored_example_files)
stdbool_h_path = posixpath.join(examples_dir, 'stdbool.h')
shutil.copy2(stdbool_h_path, examples_destination)
def write_product_sets(dock=None, information=None):
"""
Writes product information to file.
arguments:
dock (str): path to root or dock directory for source and product
directories and files.
information (object): information to write to file.
raises:
returns:
"""
# Specify directories and files.
path_tissue = os.path.join(dock, "tissue")
utility.create_directory(path_tissue)
path_sets = os.path.join(path_tissue, "sets")
# Remove previous files since they change from run to run.
utility.remove_directory(path=path_sets)
utility.create_directory(path_sets)
# Iterate on sets.
for set in information["sets"]:
# Access information.
tissue = set["tissue"]
data_sample = set["sample"]
data_gene = set["gene"]
# Specify directories and files.
path_sample = os.path.join(
path_sets, (tissue + "_samples.tsv")
)
path_gene = os.path.join(
path_sets, (tissue + "_genes.tsv")
)
# Write information to file.
data_sample.to_csv(
path_or_buf=path_sample,
sep="\t",
header=True,
index=True,
)
data_gene.to_csv(
path_or_buf=path_gene,
sep="\t",
header=True,
index=True,
)
pass
pass
def package_release():
package_name = config.get_serialization_release_name()
package_path = posixpath.join(config.BUILD_DIR, package_name)
utility.remove_directory(package_path)
shutil.copytree(config.RELEASE_DIR, package_path)
package_format = 'gztar'
if config.PLATFORM_SYSTEM == 'Windows':
package_format = 'zip'
filename = distutils.archive_util.make_archive(package_path, package_format,
root_dir=config.BUILD_DIR, base_dir=package_name)
logger.info("Release artifact package filename is \'%s\'", filename)
def execute_procedure(dock=None):
"""
Function to execute module's main behavior.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
raises:
returns:
"""
# Remove previous files to avoid version or batch confusion.
path_split = os.path.join(dock, "split")
utility.remove_directory(path=path_split)
# Read source information from file.
source = read_source(dock=dock)
split_report_write_genes_signals(
cohort="selection",
persons=source["persons_sets"]["selection"],
data_samples_tissues_persons=source["data_samples_tissues_persons"],
data_gene_signal=source["data_gene_signal"],
path_directory=os.path.join(dock, "split", "selection"),
report=True,
)
split_report_write_genes_signals(
cohort="respiration",
persons=source["persons_sets"]["respiration"],
data_samples_tissues_persons=source["data_samples_tissues_persons"],
data_gene_signal=source["data_gene_signal"],
path_directory=os.path.join(dock, "split", "respiration"),
report=True,
)
split_report_write_genes_signals(
cohort="ventilation",
persons=source["persons_sets"]["ventilation"],
data_samples_tissues_persons=source["data_samples_tissues_persons"],
data_gene_signal=source["data_gene_signal"],
path_directory=os.path.join(dock, "split", "ventilation"),
report=True,
)
pass
def initialize_directories(dock=None):
"""
Initialize directories for procedure's product files.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
raises:
returns:
(dict<str>): collection of paths to directories for procedure's files
"""
# Collect paths.
paths = dict()
# Define paths to directories.
paths["dock"] = dock
paths["stratification"] = os.path.join(paths["dock"], "stratification")
# Remove previous files to avoid version or batch confusion.
utility.remove_directory(path=paths["stratification"])
utility.create_directory(path=paths["stratification"])
# Define paths for cohorts of persons.
cohorts = list()
cohorts.append("selection")
cohorts.append("respiration")
cohorts.append("ventilation")
for cohort in cohorts:
paths[cohort] = dict()
paths[cohort]["component"] = os.path.join(paths["stratification"],
cohort, "component")
paths[cohort]["regression"] = os.path.join(paths["stratification"],
cohort, "regression")
paths[cohort]["summary"] = os.path.join(paths["stratification"],
cohort, "summary")
# Initialize directories.
utility.create_directories(path=paths[cohort]["component"])
utility.create_directories(path=paths[cohort]["regression"])
utility.create_directories(path=paths[cohort]["summary"])
# Return information.
return paths
def execute_procedure(dock=None):
"""
Function to execute module's main behavior.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
raises:
returns:
"""
if False:
# Remove previous files to avoid version or batch confusion.
path_expecto = os.path.join(dock, "expecto")
utility.remove_directory(path=path_expecto)
path_remote = "http://deepsea.princeton.edu/media/code/expecto/combined_snps.0.3.zip"
path_local = os.path.join(path_expecto, "combined_snps.0.3.zip")
utility.remove_file(path_local)
wget.download(path_remote, path_local)
utility.decompress_file_gzip(path_local)
# Read source information from file.
source = read_source(dock=dock)
print(source["data_expecto"])
# Compile information.
information = {"data_expecto": source["data_expecto"]}
#Write product information to file.
write_product(dock=dock, information=information)
pass
def run(self):
"""
Run application
:return:
"""
join_df = self.join_df
self.persist()
# Create dataframes for intersection , cogo labs and liveworks only dataframes
logger.info(
" Creating common dataframe emd5 present both in live works and cogo labs"
)
"""
Cogo labs
emd5 Name
1 Sam
2 Henry
Liveworks
emd5 Name
2 John
3 Smith
Full Outer Join
c_emd5 l_emd5 c_name l_name
1 Null Sam Null
2 2 Henry John
Null 3 Null Smith
Intersection from cogo labs and Live works, where c_emd5 and l_emd5 is not null
c_emd5 l_emd5 c_name l_name
2 2 Henry John
Users only from cogo labs, where c_emd5 is not null and l_emd5 is null
c_emd5 l_emd5 c_name l_name
1 Null Sam Null
Users only from live works, where l_emd is not null and c_emd5 is null
c_emd5 l_emd5 c_name l_name
Null 3 Null Smith
"""
common_df = join_df.filter(~join_df.emd5.isNull()
& ~join_df.cogo_emd5.isNull())
logger.info(
" Creating cogo labs only dataframe where emd5 present in cogo labs and not present in live works"
)
cogo_labs_only_df = join_df.filter(~join_df.cogo_emd5.isNull()
& join_df.emd5.isNull())
logger.info(
" Creating live works only dataframe where emd5 present in liveworks and not present in cogo labs"
)
live_works_only_df = join_df.filter(join_df.cogo_emd5.isNull()
& ~join_df.emd5.isNull())
# counting distinct emd5 counts
intersection_count = common_df.select(
common_df.cogo_emd5).distinct().count()
cogo_labs_only_count = cogo_labs_only_df.select(
cogo_labs_only_df.cogo_emd5).distinct().count()
live_works_only_count = live_works_only_df.select(
live_works_only_df.emd5).distinct().count()
logger.info(
"Number of Unique users present in both cogo labs and liveworks %s",
intersection_count)
logger.info("Number of Unique users present only in cogo labs data %s",
cogo_labs_only_count)
logger.info(
"Number of Unique users present only in live works data %s",
live_works_only_count)
# Create common job data frame with users having same job title
logger.info(
"Creating common job data frame where common users have same job title"
)
common_job_df = common_df.where(common_df.cogo_job == common_df.job)
common_job_df.persist(StorageLevel.DISK_ONLY)
print("Output with common emd5 users having same job title")
common_job_df.show()
common_job_count = common_job_df.count()
# Calculate percentage common emd5 users have different job titles
different_jobs_percent = (
(intersection_count - common_job_count) / intersection_count) * 100
logger.info(
"Number of users with common job present in both cogo labs and liveworks %s",
common_job_df.count())
logger.info("Percent have different job titles in intersection %s",
different_jobs_percent)
# jsonsify data from common data frame
"""
Create Key:Value pair
Key = Job title , Value = Company Name
cogolabs_emd5 cogolabs_job cogolabs_company liveworks_job liveworks_company
1 Hotel manager Bender PLC Barrister Brown PLC
1 Immigration officer Diaz Ltd
cogolabs_emd5 cogo_labs_c liveworks_c
1 {"Hotel manager":"Bender PLC"} {"Barrister":"Brown PLC"}
1 {"Immigration officer":"Diaz Ltd"}
"""
common_json_df = common_df.withColumn("live_works_c", concat(lit("{\""), common_df.job, lit("\":\""),
common_df.company, lit("\"}"))) \
.withColumn("cogo_labs_c", concat(lit("{\""), common_df.cogo_job,
lit("\":\""), common_df.cogo_company, lit("\"}")))
"""
Concatenate results to form Array of key value pairs group by emd5
emd5 cogolabs_json liveworks_json
1 [{"Hotel manager":"Bender PLC"},{"Immigration officer":"Diaz Ltd"}] [{"Barrister":"Brown PLC"}]
"""
common_agg_df = common_json_df.select(common_json_df.emd5, common_json_df.cogo_labs_c,
common_json_df.live_works_c) \
.groupBy(common_json_df.emd5).agg(concat_ws(",", collect_list(common_json_df.cogo_labs_c)),
concat_ws(",", collect_list(common_json_df.live_works_c))) \
.withColumnRenamed("concat_ws(,, collect_list(cogo_labs_c))", "cogo_labs_json") \
.withColumnRenamed("concat_ws(,, collect_list(live_works_c))", "live_works_json")
final_df = common_agg_df.withColumn("cogo_labs_json",
concat(lit("["), common_agg_df.cogo_labs_json, lit("]"))) \
.withColumn("live_works_json", concat(lit("["), common_agg_df.live_works_json, lit("]")))
print("Final output with emd5 , cogolabs json and liveworks json")
final_df.persist(StorageLevel.DISK_ONLY)
final_df.show()
# save final output as csv
if os.path.exists("data/final_output/"):
remove_directory("data/final_output/")
logger.info("Save final output as csv")
final_df.repartition(1).write.format("csv").save(
os.path.join(DATA_PATH, "final_output"))
self.unpersist()
def initialize_directories(dock=None):
"""
Initialize directories for procedure's product files.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
raises:
returns:
(dict<str>): collection of paths to directories for procedure's files
"""
# Collect paths.
paths = dict()
# Define paths to directories.
paths["dock"] = dock
paths["candidacy"] = os.path.join(paths["dock"], "candidacy")
# Remove previous files to avoid version or batch confusion.
utility.remove_directory(path=paths["candidacy"])
utility.create_directory(path=paths["candidacy"])
# Define paths for cohorts of persons.
cohorts = list()
cohorts.append("selection")
cohorts.append("respiration")
cohorts.append("ventilation")
for cohort in cohorts:
paths[cohort] = dict()
paths[cohort]["threshold"] = os.path.join(
paths["candidacy"], cohort, "threshold"
)
# Define paths for groups of genes by their distributions.
paths[cohort]["distribution"] = dict()
paths[cohort]["distribution"]["multimodal"] = os.path.join(
paths["candidacy"], cohort, "distribution", "multimodal"
)
paths[cohort]["distribution"]["unimodal"] = os.path.join(
paths["candidacy"], cohort, "distribution", "unimodal"
)
paths[cohort]["distribution"]["nonmultimodal"] = os.path.join(
paths["candidacy"], cohort, "distribution", "nonmultimodal"
)
paths[cohort]["distribution"]["any"] = os.path.join(
paths["candidacy"], cohort, "distribution", "any"
)
# Initialize directories.
utility.create_directories(path=paths[cohort]["threshold"])
utility.create_directories(
path=paths[cohort]["distribution"]["any"]
)
utility.create_directories(
path=paths[cohort]["distribution"]["multimodal"]
)
utility.create_directories(
path=paths[cohort]["distribution"]["unimodal"]
)
utility.create_directories(
path=paths[cohort]["distribution"]["nonmultimodal"]
)
# Return information.
return paths
def clean_sdk(self):
"""Deletes SDK that has been unpacked"""
utility.remove_directory(self.path)
def execute_procedure(dock=None):
"""
Function to execute module's main behavior.
arguments:
dock (str): path to root or dock directory for source and product
directories and files
raises:
returns:
"""
# Remove previous files.
# Specify directories and files.
path_metric = os.path.join(dock, "metric")
utility.create_directory(path_metric)
path_figure = os.path.join(path_metric, "figure")
utility.remove_directory(path=path_figure)
# Read source information from file.
#source = read_source(dock=dock)
utility.print_terminal_partition(level=1)
print("Test of metrics of modality.")
# Unimodal normal distribution.
utility.print_terminal_partition(level=2)
print("Simulation on 1,000,000 random values with a unimodal normal " +
"distribution.")
print("Expectations for unimodal normal distribution...")
print("skewness = 0")
print("kurtosis = 0")
print("bimodality coefficient < 0.55")
print("dip statistic < 0.05")
utility.print_terminal_partition(level=3)
# Generate random values with a normal distribution.
series = generate_random_values_normal(mean=1.0,
deviation=3.0,
count=1000000,
method="random")
report_metrics(name="unimodality", series=series, dock=dock)
utility.print_terminal_partition(level=3)
# Bimodal normal distribution 1.
utility.print_terminal_partition(level=2)
print("Simulation on 1,000,000 random values with a bimodal normal " +
"distribution.")
print("Expectations for bimodal normal distribution...")
print("skewness = ?")
print("kurtosis = ?")
print("bimodality coefficient > 0.55")
print("dip statistic > 0.05")
utility.print_terminal_partition(level=3)
# Generate random values with a normal distribution.
series_one = generate_random_values_normal(mean=1.0,
deviation=1.0,
count=500000,
method="random")
series_two = generate_random_values_normal(mean=5.0,
deviation=2.0,
count=500000,
method="random")
#series_one.extend(series_two)
series = series_one + series_two
report_metrics(name="bimodality_1", series=series, dock=dock)
utility.print_terminal_partition(level=3)
# Bimodal normal distribution 2.
utility.print_terminal_partition(level=2)
print("Simulation on 1,000,000 random values with a bimodal normal " +
"distribution.")
print("Expectations for bimodal normal distribution...")
print("skewness = ?")
print("kurtosis = ?")
print("bimodality coefficient > 0.55")
print("dip statistic > 0.05")
utility.print_terminal_partition(level=3)
# Generate random values with a normal distribution.
series_one = generate_random_values_normal(mean=1.0,
deviation=1.0,
count=500000,
method="random")
series_two = generate_random_values_normal(mean=10.0,
deviation=2.0,
count=500000,
method="random")
#series_one.extend(series_two)
series = series_one + series_two
report_metrics(name="bimodality_2", series=series, dock=dock)
utility.print_terminal_partition(level=3)
# Bimodal normal distribution 3.
utility.print_terminal_partition(level=2)
print("Simulation on 1,000,000 random values with a bimodal normal " +
"distribution.")
print("Expectations for bimodal normal distribution...")
print("skewness = ?")
print("kurtosis = ?")
print("bimodality coefficient > 0.55")
print("dip statistic > 0.05")
utility.print_terminal_partition(level=3)
# Generate random values with a normal distribution.
series_one = generate_random_values_normal(mean=1.0,
deviation=1.0,
count=100000,
method="random")
series_two = generate_random_values_normal(mean=10.0,
deviation=2.0,
count=900000,
method="random")
#series_one.extend(series_two)
series = series_one + series_two
report_metrics(name="bimodality_3", series=series, dock=dock)
utility.print_terminal_partition(level=3)
# Compile information.
information = {}
#Write product information to file.
#write_product(dock=dock, information=information)
pass
def clean_sdk(self):
"""Deletes SDK that has been unpacked"""
utility.remove_directory(self.path)
