Samir Sheriff samiriff

## mars_query_results.py
query_processor = QueryProcessor()
query_results = query_processor.query_files_urls(target, mission, instrument, product_type,
                                                 western_lon, eastern_lon, min_lat, max_lat,
                                                 min_ob_time, max_ob_time, product_id, file_name,
                                                 number_product_limit, result_offset_number)
print("Total Number of Files of all bin types =", len(query_results.keys()))
query_result_processor = QueryResultProcessor()
should_continue = query_result_processor.download(query_results, bin_type)
if should_continue:
  query_result_processor.process(SAVE_DIR_PREFIX, CHUNK_SIZE, SKIP_BLACK_IMAGES, ALIGN_AND_CROP_THRESHOLDS)

## mars_chunks_settings.py
# Chunk Settings
SAVE_DIR_PREFIX = './chunks'
CHUNK_SIZE = 1024
SKIP_BLACK_IMAGES = True  # Set to False to retain all images that contain black pixels

# Default Settings to Align and Crop images with black margins
MAX_BORDER_SIZE = 200   # Border to be checked around the image
SAFETY_MARGIN = 0       # Removes extra pixels from the sides to make sure no black remains
TOLERANCE = 10          # A gray value is more likely to be considered black when you increase the tolerance
ALIGN_AND_CROP_THRESHOLDS = (MAX_BORDER_SIZE, SAFETY_MARGIN, TOLERANCE) # Set to None to prevent alignment and cropping

## mars_query_parameters.py
target = 'mars'  # Aimed planetary body, i.e., Mars, Mercury, Moon, Phobos, or Venus
mission = 'MRO'  # Aimed mission, e.g., MGS or MRO
instrument = 'HIRISE'  # Aimed instrument from the mission, e.g., HIRISE or CRISM
product_type = 'RDRV11'  # Type of product to look for, e.g., DTM or RDRV11
western_lon = 234.24  # Western longitude to look for the data, from 0 to 360
eastern_lon = 234.25  # Eastern longitude to look for the data, from 0 to 360
min_lat = 68.21  # Minimal latitude to look for the data, from -90 to 90
max_lat = 68.22  # Maximal latitude to look for the data, from -90 to 90
product_id = '*RED*'  # PDS Product Id to look for, with wildcards (*) allowed
min_ob_time = ''  # Minimal observation time in (even partial) UTC format, e.g., '2017-03-01'

## mars_imports.py
from ode_data_access.query_processor import QueryProcessor
from ode_data_access.query_result_processor import QueryResultProcessor

## demo-magic.sh
#!/usr/bin/env bash

###############################################################################
#
# demo-magic.sh
#
# Copyright (c) 2015 Paxton Hare
#
# This script lets you script demos in bash. It runs through your demo script when you press
# ENTER. It simulates typing and runs commands.

## author_rules.csv

          
            Rule
             Example Match
             Regex Rule

            
              {First Name}
               Loki
               ([\w]+):

            
              {First Name} {Last Name}
               Tony Stark
               ([\w]+[\s]+[\w]+):

            
              {First Name} {Middle Name} {Last Name}
               Peter Benjamin Parker
               ([\w]+[\s]+[\w]+[\s]+[\w]+):

            
              {Mobile Number (India)}
               +91 12345 67890
               ([+]\d{2} \d{5} \d{5}):

            
              {Mobile Number (US)}
               +12 345 678 901
               ([+]\d{2} \d{3} \d{3} \d{4}):

            
              {Mobile Number (Europe)}
               +12 3456 78901
               ([+]\d{2} \d{4} \d{7})

## hour_value_counts.py
messages_df['Hour'].value_counts().head(10).sort_index(ascending=False).plot.barh() # Top 10 Hours of the day during which the most number of messages were sent
plt.xlabel('Number of messages')
plt.ylabel('Hour of Day')

## hour.py
messages_df['Hour'] = messages_df['Time'].apply(lambda x : x.split(':')[0]) # The first token of a value in the Time Column contains the hour (Eg., "20" in "20:15")

## time.py
messages_df['Time'].value_counts().head(10).plot.barh() # Top 10 Times of the day at which the most number of messages were sent
plt.xlabel('Number of messages')
plt.ylabel('Time')

## time.py
messages_df['Date'].value_counts().head(10).plot.barh() # Top 10 Dates on which the most number of messages were sent
plt.xlabel('Number of Messages')
plt.ylabel('Date')
	query_processor = QueryProcessor()
	query_results = query_processor.query_files_urls(target, mission, instrument, product_type,
	western_lon, eastern_lon, min_lat, max_lat,
	min_ob_time, max_ob_time, product_id, file_name,
	number_product_limit, result_offset_number)
	print("Total Number of Files of all bin types =", len(query_results.keys()))
	query_result_processor = QueryResultProcessor()
	should_continue = query_result_processor.download(query_results, bin_type)
	if should_continue:
	query_result_processor.process(SAVE_DIR_PREFIX, CHUNK_SIZE, SKIP_BLACK_IMAGES, ALIGN_AND_CROP_THRESHOLDS)
	# Chunk Settings
	SAVE_DIR_PREFIX = './chunks'
	CHUNK_SIZE = 1024
	SKIP_BLACK_IMAGES = True # Set to False to retain all images that contain black pixels

	# Default Settings to Align and Crop images with black margins
	MAX_BORDER_SIZE = 200 # Border to be checked around the image
	SAFETY_MARGIN = 0 # Removes extra pixels from the sides to make sure no black remains
	TOLERANCE = 10 # A gray value is more likely to be considered black when you increase the tolerance
	ALIGN_AND_CROP_THRESHOLDS = (MAX_BORDER_SIZE, SAFETY_MARGIN, TOLERANCE) # Set to None to prevent alignment and cropping
	target = 'mars' # Aimed planetary body, i.e., Mars, Mercury, Moon, Phobos, or Venus
	mission = 'MRO' # Aimed mission, e.g., MGS or MRO
	instrument = 'HIRISE' # Aimed instrument from the mission, e.g., HIRISE or CRISM
	product_type = 'RDRV11' # Type of product to look for, e.g., DTM or RDRV11
	western_lon = 234.24 # Western longitude to look for the data, from 0 to 360
	eastern_lon = 234.25 # Eastern longitude to look for the data, from 0 to 360
	min_lat = 68.21 # Minimal latitude to look for the data, from -90 to 90
	max_lat = 68.22 # Maximal latitude to look for the data, from -90 to 90
	product_id = 'RED' # PDS Product Id to look for, with wildcards (*) allowed
	min_ob_time = '' # Minimal observation time in (even partial) UTC format, e.g., '2017-03-01'
	from ode_data_access.query_processor import QueryProcessor
	from ode_data_access.query_result_processor import QueryResultProcessor
	#!/usr/bin/env bash

	###############################################################################
	#
	# demo-magic.sh
	#
	# Copyright (c) 2015 Paxton Hare
	#
	# This script lets you script demos in bash. It runs through your demo script when you press
	# ENTER. It simulates typing and runs commands.
Rule	Example Match	Regex Rule
{First Name}	Loki	([\w]+):
{First Name} {Last Name}	Tony Stark	([\w]+[\s]+[\w]+):
{First Name} {Middle Name} {Last Name}	Peter Benjamin Parker	([\w]+[\s]+[\w]+[\s]+[\w]+):
{Mobile Number (India)}	+91 12345 67890	([+]\d{2} \d{5} \d{5}):
{Mobile Number (US)}	+12 345 678 901	([+]\d{2} \d{3} \d{3} \d{4}):
{Mobile Number (Europe)}	+12 3456 78901	([+]\d{2} \d{4} \d{7})
	messages_df['Hour'].value_counts().head(10).sort_index(ascending=False).plot.barh() # Top 10 Hours of the day during which the most number of messages were sent
	plt.xlabel('Number of messages')
	plt.ylabel('Hour of Day')
	messages_df['Time'].value_counts().head(10).plot.barh() # Top 10 Times of the day at which the most number of messages were sent
	plt.xlabel('Number of messages')
	plt.ylabel('Time')
	messages_df['Date'].value_counts().head(10).plot.barh() # Top 10 Dates on which the most number of messages were sent
	plt.xlabel('Number of Messages')
	plt.ylabel('Date')