def __init__(self, dbconn=None, **kw):
HTMLWriter.__init__(self)
self.master = MasterDB(dbconn=dbconn)
# self.master.db.get_cursor()
self.dbconn = self.master.db.conn
self.kw = {'form_pv':'', 'pv':'', 'inst_id':-1,'submit':''}
self.kw.update(kw)
def __init__(self,dbconn=None,**kw):
HTMLWriter.__init__(self)
self.arch = Instruments(dbconn=dbconn)
self.dbconn = self.arch.dbconn
self.kw = {'station_sel':'', 'newstation':'',
'station':'', 'instrument':'','pv':'',
'station_add':'','inst_id':-1,
'submit': '' }
def main():
# mtk? get command line arguments
#Change this to a functions
InputFileNameElements = [ "WebsiteSearchDetails.txt" ]
OutputFileNameElements = [ "Reports", "Report.json" ]
# read each line in input file and store
# get_stolen_website_details() returns a list including string or URL and further list of Search Terms
for WebsiteUrl, SearchItems in get_auction_website_details(InputFileNameElements):
print("Getting search items for " + WebsiteUrl)
# mtk - insert logic here for different website details...
# class StolenAuctionSoup takes SearchItems and locates results accordingly
GumTreeSoup = StolenAuctionSoup()
# from each stored line in WebsiteSearchDetails.txt get specific URL
MyUrl = GumTreeSoup.create_url_request(WebsiteUrl, SearchItems)
# send URl request to specific website using Beautiful Soup
MySoup = GumTreeSoup.get_soup(MyUrl)
# mtk 07.17 - added code to save each report to a Unique folder with name made up from search details
UniqueOutputFileNameElements = create_unique_report_file_name(OutputFileNameElements, SearchItems)
# use this same information for SubHeading in HTML report
SubHeading = return_string_with_each_search_term(SearchItems)
# Create instance of HTML (Report) Writer
HTMLReport = HTMLWriter()
HTMLReport.create_html_file(UniqueOutputFileNameElements)
HTMLReport.add_main_heading(WebsiteUrl)
HTMLReport.add_sub_heading(SubHeading)
HTMLReport.add_table_by_id(WebsiteUrl)
# examine the specific results from GumTree.com (function contains yield)
for CurrentItem in GumTreeSoup.get_website_items(MySoup, os.path.dirname(os.path.join(*UniqueOutputFileNameElements))):
print ("Reporting current item..." + CurrentItem[0])
# ..and add details to report,
HTMLReport.add_table_data_by_id(WebsiteUrl, CurrentItem)
# along with any related images
HTMLReport.add_table_data_image_by_id(WebsiteUrl, GumTreeSoup.CurrentDownloadedImageFileName)
# create report with specified imputs
HTMLReport.write_html_report_and_close(2)
def main():
extract_prefix = "AoT_Taiwan.complete"
extract_tarpath = "{0}.{1}".format(
extract_prefix,
datetime.datetime.now().strftime("%Y-%m-%d"))
clear_data(extract_tarpath)
writer = HTMLWriter()
urllib3.disable_warnings()
temp_filename = "temp.tar"
target_url = "https://www.mcs.anl.gov/research/projects/waggle/downloads/datasets/AoT_Taiwan.complete.recent.tar"
if not os.path.isdir(extract_tarpath):
download_record(target_url, temp_filename)
with tarfile.open(temp_filename) as tf:
tf.extract(extract_tarpath + "/data.csv.gz")
tf.extract(extract_tarpath + "/nodes.csv")
console_format("Extract Done!")
console_format("Processing...")
node_list = ['0CC', '110', '0FD']
# node_list = ['0FD']
df_nodes = pd.read_csv(extract_tarpath + "/nodes.csv")
df_nodes = df_nodes[df_nodes['vsn'].isin(node_list)]
df_nodes = df_nodes[['node_id', 'vsn']]
sensor_param = {
'co': ["concentration"],
'h2s': ["concentration"],
'no2': ["concentration"],
'o3': ["concentration"],
'so2': ["concentration"],
'pms7003': ["1um_particle", "2_5um_particle", "10um_particle"],
'bmp180': ["pressure", "temperature"],
'hih4030': ["humidity"],
'hih6130': ["humidity", "temperature"],
'htu21d': ["humidity", "temperature"],
'lps25h': ["temperature"],
'pr103j2': ["temperature"],
'tsys01': ["temperature"],
'tmp421': ["temperature"],
'tmp112': ["temperature"],
'mma8452q': ["acceleration_x", "acceleration_y", "acceleration_z"],
'bmi160': [
"acceleration_x", "acceleration_y", "acceleration_z",
"orientation_x", "orientation_y", "orientation_z"
],
'hmc5883l':
["magnetic_field_x", "magnetic_field_y", "magnetic_field_z"],
'tsl260rd': ["intensity"],
'ml8511': ["intensity"],
'mlx75305': ["intensity"],
'si1145': [
"intensity", "ir_intensity", "uv_intensity",
"visible_light_intensity"
],
'tsl250rd': ["intensity"],
'apds_9006_020': ["intensity"],
'spv1840lr5h_b': ["intensity"],
'image_detector': ["car_total", "person_total"]
}
flatten_param = list(dict.fromkeys(
itertools.chain(*sensor_param.values())))
df_data = pd.read_csv(extract_tarpath + "/data.csv.gz", compression='gzip')
df_data = df_data[df_data['sensor'].isin(list(sensor_param.keys()))]
# df_data = df_data[df_data['parameter'].isin(flatten_param)].reset_index()
# df_data = df_data.drop(columns='index')
drop_rows = list()
for index, row in df_data.iterrows():
if not row['parameter'] in sensor_param[row['sensor']]:
drop_rows.append(index)
df_data = df_data.drop(index=drop_rows)
df_data = pd.merge(df_nodes, df_data, on='node_id')
df_data['timestamp'] = pd.to_datetime(df_data['timestamp'])
df_data = df_data.groupby(
['node_id', 'vsn', 'subsystem', 'sensor',
'parameter']).last().reset_index()
df_data['value_raw'] = df_data['value_raw'].astype('float64')
df_data['value_hrf'] = df_data['value_hrf'].astype('float64')
cols = df_data.columns.tolist()
cols.insert(0, cols.pop(cols.index('vsn')))
df_data = df_data.reindex(columns=cols)
output_filename = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
df_data.to_excel(output_filename + ".xlsx")
writer.write(df_data, output_filename + ".html")
# clear_temp()
console_format("Done!")