wbhinton

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO

path = "pdf/*.pdf"

def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()

wbhinton

import PyPDF2
import textract
import nltk
import re
from tika import parser
import heapq 
import glob

sys.stdout = codecs.getwriter("iso-8859-1")(sys.stdout, 'xmlcharrefreplace')

wbhinton

from sklearn.preprocessing import MinMaxScaler
# Import models
from pyod.models.cblof import CBLOF
from pyod.models.feature_bagging import FeatureBagging
from pyod.models.hbos import HBOS
from pyod.models.iforest import IForest
from pyod.models.knn import KNN
from pyod.models.lof import LOF
import matplotlib
df['X1'] = df['X']

wbhinton

SELECT OBJECT_SCHEMA_NAME(c.object_id) SchemaName
	,o.Name AS Table_Name
	,c.Name AS Field_Name
	,t.Name AS Data_Type
	,t.max_length AS Length_Size
	,t.precision AS Precision
FROM sys.columns c
INNER JOIN sys.objects o ON o.object_id = c.object_id
LEFT JOIN sys.types t ON t.user_type_id = c.user_type_id
WHERE o.type = 'U'

wbhinton

SELECT @@Servername AS ServerName ,
    DB_NAME() AS DB_Name ,
    o.Name AS TableName ,
    i.Name AS IndexName
FROM sys.objects o
    INNER JOIN sys.indexes i ON o.object_id = i.object_id
WHERE   o.Type = 'U' -- User table 
    AND LEFT(i.Name, 1) <> '_'
-- Remove hypothetical indexes 

wbhinton

-- How to find the hierarchical dependencies
-- Solve recursive queries using Common Table Expressions (CTE)
WITH
    TableHierarchy ( ParentTable, DependentTable, Level )
    AS
    (
        -- Anchor member definition (First level group to start the process)
                    SELECT DISTINCT
                CAST(NULL AS INT) AS ParentTable ,

wbhinton

-- Foreign Keys 
SELECT @@Servername AS ServerName ,
    DB_NAME() AS DB_Name ,
    parent.name AS 'TableName' ,
    o.name AS 'ForeignKey' ,
    o.[Type] ,
    o.Create_date
FROM sys.objects o
    INNER JOIN sys.objects parent ON o.parent_object_id = parent.object_id

wbhinton

-- Heap tables (Method 1) 
SELECT @@Servername AS ServerName ,
    DB_NAME() AS DBName ,
    t.Name AS HeapTable ,
    t.Create_Date
FROM sys.tables t
    INNER JOIN sys.indexes i ON t.object_id = i.object_id
        AND i.type_desc = 'HEAP'
ORDER BY t.Name

wbhinton

-- This works for T-SQL
SELECT u.name + '.' + t.name AS [table],
    td.value AS [table_desc],
    c.name AS [column],
    cd.value AS [column_desc]
FROM sysobjects t
    INNER JOIN sysusers u
    ON      u.uid = t.uid
    LEFT OUTER JOIN sys.extended_properties td
    ON      td.major_id = t.id

wbhinton

-- Similar information can be derived from sp_who 
SELECT @@Servername AS Server ,
    DB_NAME(database_id) AS DatabaseName ,
    COUNT(database_id) AS Connections ,
    Login_name AS LoginName ,
    MIN(Login_Time) AS Login_Time ,
    MIN(COALESCE(last_request_end_time, last_request_start_time))
                                                         AS Last_Batch
FROM sys.dm_exec_sessions
WHERE   database_id > 0