def convert_struct_field(column: StructField) -> TableDefinition.Column:
"""Converts a Spark StructField to a Tableau Hyper SqlType"""
if column.dataType == IntegerType():
sql_type = SqlType.int()
elif column.dataType == LongType():
sql_type = SqlType.big_int()
elif column.dataType == ShortType():
sql_type = SqlType.small_int()
elif column.dataType == DoubleType():
sql_type = SqlType.double()
elif column.dataType == FloatType():
sql_type = SqlType.double()
elif column.dataType == BooleanType():
sql_type = SqlType.bool()
elif column.dataType == DateType():
sql_type = SqlType.date()
elif column.dataType == TimestampType():
sql_type = SqlType.timestamp()
elif column.dataType == StringType():
sql_type = SqlType.text()
else:
# Trap the DecimalType case
if str(column.dataType).startswith("DecimalType"):
# Max precision is only up to 18 decimal places in Tableau Hyper API
precision = column.dataType.precision if column.dataType.precision <= 18 else 18
scale = column.dataType.scale
sql_type = SqlType.numeric(precision, scale)
else:
raise ValueError(f'Invalid StructField datatype for column `{column.name}` : {column.dataType}')
nullable = NULLABLE if column.nullable else NOT_NULLABLE
return TableDefinition.Column(name=column.name, type=sql_type, nullability=nullable)
def fn_convert_to_hyper_types(given_type):
switcher = {
'empty': SqlType.text(),
'bool': SqlType.bool(),
'int': SqlType.big_int(),
'float-dot': SqlType.double(),
'date-YMD': SqlType.date(),
'date-MDY': SqlType.date(),
'date-DMY': SqlType.date(),
'time-24': SqlType.time(),
'time-12': SqlType.time(),
'datetime-24-YMD': SqlType.timestamp(),
'datetime-12-MDY': SqlType.timestamp(),
'datetime-24-DMY': SqlType.timestamp(),
'str': SqlType.text()
}
identified_type = switcher.get(given_type)
if identified_type is None:
identified_type = SqlType.text()
return identified_type
def createHyperTable():
columns = getConfig()
page_table = TableDefinition(table_name="Page")
for i in range(0, len(columns)):
if columns[i]['DataType'] == "String":
dt = SqlType.text()
elif columns[i]['DataType'] == "Date":
dt = SqlType.date()
else:
dt = SqlType.big_int()
page_table.add_column(columns[i]['ColumnName'], dt)
return page_table
def df_to_extract(df, output_path):
'''
Converts a Pandas dataframe to a Tableau Extract.
Parameters
----------
df (pandas dataframe): Dataframe to turn into a Tableau extract
output_path (str): Where to create the Tableau extract
'''
# Replace nan's with 0
df = df.replace(np.nan, 0.0, regex=True)
print('Creating Tableau data extract...')
with HyperProcess(telemetry=Telemetry.DO_NOT_SEND_USAGE_DATA_TO_TABLEAU) as hyper:
with Connection(hyper.endpoint, output_path, CreateMode.CREATE_AND_REPLACE) as connection:
# Create schema
connection.catalog.create_schema('Extract')
# Create list of column definitions, based on the datatypes in pandas dataframe
dtype_map = {
'int32': SqlType.int(),
'int64': SqlType.big_int(),
'float32': SqlType.double(),
'float64': SqlType.double(),
'datetime64[ns]': SqlType.date(),
'object': SqlType.text()
}
table_def = []
# Get column headers to loop through them
df_columns = list(df)
for col_header in df_columns:
dtype_str = str(df[col_header].dtype)
# Use dtype_str to lookup appropiate SqlType from dtype_map and append new column to table definition
table_def.append(TableDefinition.Column(col_header, dtype_map[dtype_str]))
# Define table
extract_table = TableDefinition(TableName('Extract', 'Extract'), table_def)
# Create table
connection.catalog.create_table(extract_table)
# Insert data
with Inserter(connection, extract_table) as inserter:
for idx, row in df.iterrows():
inserter.add_row(row)
inserter.execute()
def test_convert_struct_field(self):
# ensure strings can be converted correctly
first_name_col = StructField('first_name', StringType(), False)
converted_col = convert_struct_field(first_name_col)
assert (converted_col.name == Name('first_name'))
assert (converted_col.nullability is NOT_NULLABLE)
assert (converted_col.type == SqlType.text())
# ensure dates can be converted correctly
date_col = StructField('update_date', DateType(), True)
converted_col = convert_struct_field(date_col)
assert (converted_col.name == Name('update_date'))
assert (converted_col.nullability is NULLABLE)
assert (converted_col.type == SqlType.date())
# ensure timestamps can be converted correctly
timestamp_col = StructField('created_at', TimestampType(), False)
converted_col = convert_struct_field(timestamp_col)
assert (converted_col.name == Name('created_at'))
assert (converted_col.nullability is NOT_NULLABLE)
assert (converted_col.type == SqlType.timestamp())
def _hyper_sql_type(self, source_column):
"""
Finds the correct Hyper column type for source_column
source_column (obj): Source column (Instance of google.cloud.bigquery.schema.SchemaField)
Returns a tableauhyperapi.SqlType Object
"""
source_column_type = source_column.field_type
return_sql_type = {
"BOOL": SqlType.bool(),
"BYTES": SqlType.bytes(),
"DATE": SqlType.date(),
"DATETIME": SqlType.timestamp(),
"INT64": SqlType.big_int(),
"INTEGER": SqlType.int(),
"NUMERIC": SqlType.numeric(18, 9),
"FLOAT64": SqlType.double(),
"STRING": SqlType.text(),
"TIME": SqlType.time(),
"TIMESTAMP": SqlType.timestamp_tz(),
}.get(source_column_type)
if return_sql_type is None:
error_message = "No Hyper SqlType defined for BigQuery source type: {}".format(
source_column_type
)
logger.error(error_message)
raise LookupError(error_message)
logger.debug(
"Translated source column type {} to Hyper SqlType {}".format(
source_column_type, return_sql_type
)
)
return return_sql_type
def Full_refresh(result):
LogFileWrite("Running Full refresh")
try:
with HyperProcess(telemetry=Telemetry.DO_NOT_SEND_USAGE_DATA_TO_TABLEAU) as hyperprocess:
print("The HyperProcess has started.")
LogFileWrite("The HyperProcess has started.")
print(hyperprocess.is_open)
if hyperprocess.is_open==True:
with Connection(hyperprocess.endpoint, 'Facebook_campaigns.hyper', CreateMode.CREATE_AND_REPLACE,) as connection:
if connection.is_open==True:
print("The connection to the Hyper file is open.")
LogFileWrite("The connection to the Hyper file is open.")
connection.catalog.create_schema('Extract')
DataTable = TableDefinition(TableName('Extract','Campaign_data'),[
############Below Columns are extracted from Report data API
TableDefinition.Column('Row_ID', SqlType.big_int()),
TableDefinition.Column('Inserted Date', SqlType.date()),
TableDefinition.Column('Date', SqlType.date()),
TableDefinition.Column('Account Id', SqlType.varchar(50)),
TableDefinition.Column('Account Name', SqlType.text()),
TableDefinition.Column('Campaign Id', SqlType.varchar(50)),
TableDefinition.Column('Campaign Name', SqlType.text()),
TableDefinition.Column('Impressions', SqlType.big_int()),
TableDefinition.Column('Clicks', SqlType.big_int()),
TableDefinition.Column('Reach', SqlType.big_int()),
TableDefinition.Column('Spend', SqlType.double()),
TableDefinition.Column('Frequency', SqlType.double()),
])
print("The table is defined.")
LogFileWrite("Successfully Facebook Campaign Table is defined")
connection.catalog.create_table(DataTable)
# print(Campaign_df["Id"].dtype)
#print(range(len(Campaign_df["Id"])))
with Inserter(connection, TableName('Extract','Campaign_data')) as inserter:
inserted_rows=1
row_id=1
for i in range(0,len(result["Campaign Id"])):
#print(str(result.loc[i,"CampaignId"]))
#print(result.loc[i,"Date"])
inserter.add_row([
int(row_id),
datetime.today(),
(datetime.strptime(result.loc[i,"Date"], '%Y-%m-%d')),
#(datetime.date(result.loc[i,"Date"])),#, "%Y-%m-%d")),
str(result.loc[i,"Account Id"]),
str(result.loc[i,"Account Name"]),
str(result.loc[i,"Campaign Id"]),
str(result.loc[i,"Campaign Name"]),
int(result.loc[i,"Impressions"]),
int(result.loc[i,"Clicks"]),
int(result.loc[i,"Reach"]),
float(result.loc[i,"Spend"]),
float(result.loc[i,"Frequency"])
])
#print("instered")
row_id=row_id+1
inserted_rows=inserted_rows+1
inserter.execute()
print("Instered Rows are " +str(inserted_rows))
LogFileWrite("Instered Rows are " +str(inserted_rows))
table_name=TableName('Extract','Campaign_data')
Delet_query=f"DELETE FROM {table_name} WHERE " +'"'+ 'Row_ID'+'"'+" NOT IN("
Delet_query+="SELECT MAX("+'"'+'Row_ID'+'"'+f") FROM {table_name} "
Delet_query+="GROUP BY " +'"'+'Date'+'",'+'"'+'Campaign Id'+'",'+'"'+'Campaign Name'+'",'
Delet_query+='"'+'Account Id'+'",'+'"'+'Impressions'+'",'
Delet_query+='"'+'Clicks'+'",'+'"'+'Account Name'+'",'+'"'+'Reach'+'",'+'"'+'Spend'+'",'
Delet_query+='"'+'Frequency'+'")'
#print(Delet_query)
connection.execute_command(Delet_query)
print("Deleted Duplicate rows")
LogFileWrite("Successfully deleted Duplicate rows")
else:
print("unable to open connection to hyper file")
LogFileWrite("unable to open connection to hyper file")
if connection.is_open==True:
connection.close()
print("Connection to Hyper file closed")
LogFileWrite("Connection to Hyper file closed")
else:
print("Connection to Hyper file closed")
LogFileWrite("Connection to Hyper file closed")
print("Connection is open or closed" + str(connection.is_open))
else:
print("Unable to start the Hyper process ")
LogFileWrite("Unable to start the Hyper process ")
if hyperprocess.is_open==True:
hyperprocess.close()
print("Forcefully shutted down the Hyper Process")
LogFileWrite("Forcefully shutted down the Hyper Process")
else:
print("Hyper process is shutted down")
LogFileWrite("Hyper process is shutted down")
print("Connection is open or closed" + str(connection.is_open))
print("process is open or closed" + str(hyperprocess.is_open))
except HyperException as ex:
LogFileWrite("There is exception in starting Tableau Hyper Process. Exiting...")
LogFileWrite(str(ex))
connection.close()
hyperprocess.close()
SendEmailMessage()
sys.exit()
import yaml
from pathlib import Path
from tableauhyperapi import HyperProcess, Telemetry, \
Connection, CreateMode, \
NOT_NULLABLE, NULLABLE, SqlType, TableDefinition, \
Inserter, \
escape_name, escape_string_literal, \
HyperException
#Create table definition to be used in Hyper file
workbook_table = TableDefinition(
table_name="Workbooks",
columns=[
TableDefinition.Column("Project Id", SqlType.text(), NOT_NULLABLE),
TableDefinition.Column("Content URL", SqlType.text(), NOT_NULLABLE),
TableDefinition.Column("Created At", SqlType.date(), NOT_NULLABLE),
TableDefinition.Column("Id", SqlType.text(), NOT_NULLABLE),
TableDefinition.Column("Project Name", SqlType.text(), NOT_NULLABLE),
TableDefinition.Column("size", SqlType.big_int(), NOT_NULLABLE),
TableDefinition.Column("Updated At", SqlType.date(), NOT_NULLABLE),
TableDefinition.Column("Name", SqlType.text(), NOT_NULLABLE)
])
#Name of hyper file that will be generated locally and deployed to Tableau
path_to_database = Path("workbooks.hyper")
#Name of project where Hyper file will be deployed
#This project must exist on your server
PROJECT = 'HyperTest'
def main():
import os
import json
import sys
from tableauhyperapi import HyperProcess, Telemetry, Connection, CreateMode, NOT_NULLABLE, NULLABLE, SqlType, TableDefinition, escape_string_literal
# SqlTypeをdictで参照
sql_type_dict = {}
sql_type_dict['BIG_INT'] = SqlType.big_int()
sql_type_dict['TEXT'] = SqlType.text()
sql_type_dict['DOUBLE'] = SqlType.double()
sql_type_dict['DATE'] = SqlType.date()
sql_type_dict['TIMESTAMP'] = SqlType.timestamp()
# NULLABLEをdictで参照
nullable_dict = {}
nullable_dict['YES'] = NULLABLE
nullable_dict['NO'] = NOT_NULLABLE
def create_column_def(table_def_dict: dict):
column_def = []
for key in table_def_dict.keys():
column_def.append(
TableDefinition.Column(
key, sql_type_dict[table_def_dict[key]['type']],
nullable_dict[table_def_dict[key]['nullable']]))
return column_def
#
with HyperProcess(Telemetry.SEND_USAGE_DATA_TO_TABLEAU, 'myapp' ) as hyper:
# Step 2: Create the the .hyper file, replace it if it already exists
with Connection(endpoint=hyper.endpoint,
create_mode=CreateMode.CREATE_AND_REPLACE,
database=path_to_hyper) as connection:
# Step 3: Create the schema
connection.catalog.create_schema('Extract')
# Step 4: Create the table definition
schema = TableDefinition(table_name=TableName('Extract','Extract'),
columns=[
TableDefinition.Column('name', SqlType.text()),
TableDefinition.Column('date', SqlType.date()),
TableDefinition.Column('temperature', SqlType.double()),
TableDefinition.Column('chance_precipitation', SqlType.double()),
TableDefinition.Column('precipitation', SqlType.double()),
TableDefinition.Column('wind_speed', SqlType.double()),
TableDefinition.Column('wind_gust', SqlType.double()),
TableDefinition.Column('visiblity', SqlType.double()),
TableDefinition.Column('cloud_cover', SqlType.double()),
TableDefinition.Column('relative_humidity', SqlType.double()),
TableDefinition.Column('moon_phase', SqlType.double()),
TableDefinition.Column('condition', SqlType.text()),
])
# Step 5: Create the table in the connection catalog
connection.catalog.create_table(schema)
escape_name, escape_string_literal, \
HyperException
# Table Definitions required to create tables
orders_table = TableDefinition(
# Since the table name is not prefixed with an explicit schema name, the table will reside in the default "public" namespace.
table_name="Orders",
columns=[
TableDefinition.Column(name="Address ID",
type=SqlType.small_int(),
nullability=NOT_NULLABLE),
TableDefinition.Column(name="Customer ID",
type=SqlType.text(),
nullability=NOT_NULLABLE),
TableDefinition.Column(name="Order Date",
type=SqlType.date(),
nullability=NOT_NULLABLE),
TableDefinition.Column(name="Order ID",
type=SqlType.text(),
nullability=NOT_NULLABLE),
TableDefinition.Column(name="Ship Date",
type=SqlType.date(),
nullability=NULLABLE),
TableDefinition.Column(name="Ship Mode",
type=SqlType.text(),
nullability=NULLABLE)
])
customer_table = TableDefinition(
# Since the table name is not prefixed with an explicit schema name, the table will reside in the default "public" namespace.
table_name="Customer",
.option("sep", cf.delimiter) \
.load(cf.input_file_path)
col = list(df.dtypes)
print(len(col))
for i in range(len(col)):
col[i] = list(col[i])
col[i][1] = type_[col[i][1]]
print(col, len(col))
xyz = [
TableDefinition.Column('cdl_uuid', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('cdl_frequency', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('cdl_effective_date', SqlType.date(), NULLABLE),
TableDefinition.Column('cdl_run_identifier', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('customer_id', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('customer_type', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('customer_name', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('customer_address', SqlType.varchar(100), NULLABLE),
TableDefinition.Column('city', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('state', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('zip', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('phone', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('fax', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('email', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('customer_status', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('metropolitan_statistical_area_name', SqlType.varchar(100), NULLABLE),
TableDefinition.Column('blocked_account', SqlType.varchar(30), NULLABLE),
TableDefinition.Column('phs', SqlType.varchar(30), NULLABLE),
def sparkConnect():
# fetching DF from spark filestore
if cf.file_type == 'csv':
df = spark.read.format(cf.file_type) \
.option("inferSchema", cf.infer_schema) \
.option("header", cf.first_row_is_header) \
.option("sep", cf.delimiter) \
.load(cf.input_file_path)
# print('\n', cf.input_file_path, '\n', cf.schema, '\n')
# fetching table from db from databricks
elif cf.file_type == 'jdbc':
df = spark.read.format("jdbc") \
.option("driver", cf.driver) \
.option("url", cf.url) \
.option("dbtable", cf.table) \
.option("user", cf.user) \
.option("password", cf.password) \
.option("inferSchema", cf.infer_schema) \
.option("header", cf.first_row_is_header) \
.load()
df.write.format("csv") \
.option("enoding", cf.charset) \
.option("header", cf.first_row_is_header) \
.option("sep", cf.delimiter) \
.save('/home/hari/HyperConverter/test')
# pdf = df.select('*').toPandas()
# path = '/home/hari/HyperConverter/test.csv'
# pdf.to_csv(path, sep=',', index=False)
path = glob.glob('/home/hari/HyperConverter/test/part*.csv')
cf.input_file_path = path[0]
cf.input_file_path = path
print('\n', cf.input_file_path, '\n')
col = list(df.dtypes)
print(col)
print(len(col))
for i in range(len(col)):
col[i] = list(col[i])
col[i][1] = type_[col[i][1]]
# print('\n', col, '\n')
x = []
for i, j in col:
print(i, j)
if j == 'varchar':
max_length = df.agg({i: "max"}).collect()[0]
#print(max_length)
xyz = max_length["max({})".format(i)]
if xyz != None:
max_length = len(xyz)
if 19 <= max_length <= 40:
max_length = 100
else:
max_length = 30
else:
max_length = 35
print(max_length)
x.append(
TableDefinition.Column(i, SqlType.varchar(max_length),
NULLABLE))
elif j == 'int':
x.append(TableDefinition.Column(i, SqlType.int(), NULLABLE))
elif j == 'date':
x.append(TableDefinition.Column(i, SqlType.date(), NULLABLE))
elif j == 'numeric':
x.append(
TableDefinition.Column(i, SqlType.numeric(10, 4), NULLABLE))
elif j == 'bool':
x.append(TableDefinition.Column(i, SqlType.bool(), NULLABLE))
elif j == 'big_int':
x.append(TableDefinition.Column(i, SqlType.big_int(), NULLABLE))
elif j == 'double':
x.append(TableDefinition.Column(i, SqlType.double(), NULLABLE))
elif j == 'text':
print("this is culprate", i, j)
x.append(TableDefinition.Column(i, SqlType.text(), NULLABLE))
print(x)
print(len(x))
return x
Connection, CreateMode, \
NOT_NULLABLE, NULLABLE, SqlType, TableDefinition, \
Inserter, \
escape_name, escape_string_literal, \
HyperException
data_table = TableDefinition(
# Since the table name is not prefixed with an explicit schema name, the table will reside in the default "public" namespace.
table_name="COVID-19",
columns=[
TableDefinition.Column("Country/Region", SqlType.text(), NOT_NULLABLE),
TableDefinition.Column("Province/State", SqlType.text(), NULLABLE),
TableDefinition.Column("Latitude", SqlType.double(), NOT_NULLABLE),
TableDefinition.Column("Longitude", SqlType.double(), NOT_NULLABLE),
TableDefinition.Column("Case_Type", SqlType.text(), NOT_NULLABLE),
TableDefinition.Column("Date", SqlType.date(), NOT_NULLABLE),
TableDefinition.Column("Cases", SqlType.big_int(), NOT_NULLABLE),
TableDefinition.Column("Difference", SqlType.big_int(), NOT_NULLABLE),
TableDefinition.Column("Last_Update_Date", SqlType.date(),
NOT_NULLABLE),
])
def run_create_hyper_file_from_csv():
"""
An example demonstrating loading data from a csv into a new Hyper file
"""
print("EXAMPLE - Load data from CSV into table in new Hyper file")
path_to_database = Path("covid-19.hyper")
from tableauhyperapi import HyperProcess, Telemetry, \
Connection, CreateMode, \
NOT_NULLABLE, NULLABLE, SqlType, TableDefinition, \
Inserter, \
escape_name, escape_string_literal, \
HyperException
# Table Definitions required to create tables
orders_table = TableDefinition(
# Since the table name is not prefixed with an explicit schema name, the table will reside in the default "public" namespace.
table_name="Orders",
columns=[
TableDefinition.Column(name="Address ID", type=SqlType.small_int(), nullability=NOT_NULLABLE),
TableDefinition.Column(name="Customer ID", type=SqlType.text(), nullability=NOT_NULLABLE),
TableDefinition.Column(name="Order Date", type=SqlType.date(), nullability=NOT_NULLABLE),
TableDefinition.Column(name="Order ID", type=SqlType.text(), nullability=NOT_NULLABLE),
TableDefinition.Column(name="Ship Date", type=SqlType.date(), nullability=NULLABLE),
TableDefinition.Column(name="Ship Mode", type=SqlType.text(), nullability=NULLABLE)
]
)
customer_table = TableDefinition(
# Since the table name is not prefixed with an explicit schema name, the table will reside in the default "public" namespace.
table_name="Customer",
columns=[
TableDefinition.Column(name="Customer ID", type=SqlType.text(), nullability=NOT_NULLABLE),
TableDefinition.Column(name="Customer Name", type=SqlType.text(), nullability=NOT_NULLABLE),
TableDefinition.Column(name="Loyalty Reward Points", type=SqlType.big_int(), nullability=NOT_NULLABLE),
TableDefinition.Column(name="Segment", type=SqlType.text(), nullability=NOT_NULLABLE)
]