Data Base management (Db)¶
Import packages¶
In [1]:
import numpy as np
import matplotlib.pyplot as plt
import gstlearn as gl
import gstlearn.plot as gp
import gstlearn.document as gdoc
gdoc.setNoScroll()
Define the Global variables
In [2]:
gl.OptCst.define(gl.ECst.NTCOL, 6)
gl.law_set_random_seed(13414)
Defining a Data set¶
The data is defined by simulating samples at random within a given box. This study is performed in 2-D but this is not considered as a limitation.
In [3]:
nech = 500
mydb = gl.Db.createFromBox(nech, [0, 0], [100, 100])
mydb
Out[3]:
Data Base Characteristics ========================= Data Base Summary ----------------- File is organized as a set of isolated points Space dimension = 2 Number of Columns = 3 Total number of samples = 500 Variables --------- Column = 0 - Name = rank - Locator = NA Column = 1 - Name = x-1 - Locator = x1 Column = 2 - Name = x-2 - Locator = x2
Displaying the Data set
In [4]:
res = gp.symbol(mydb)
We now define a vector of 0-1 integer values at random again, according to a Bernoulli distribution with a probability of 0.2. This vector is added to the Data Base.
In [5]:
sel = gl.VectorHelper.simulateBernoulli(nech, 0.2)
gl.VectorHelper.dumpStats("Statistics on the Selection vector", sel)
iuid = mydb.addColumns(sel, "sel")
Statistics on the Selection vector - Number of samples = 500 / 500 - Minimum = 0.000 - Maximum = 1.000 - Mean = 0.186 - St. Dev. = 0.389
In [6]:
dbfmt = gl.DbStringFormat.createFromFlags(flag_stats=True, names=["sel"])
mydb.display(dbfmt)
Data Base Characteristics ========================= Data Base Summary ----------------- File is organized as a set of isolated points Space dimension = 2 Number of Columns = 4 Total number of samples = 500 Data Base Statistics -------------------- 4 - Name sel - Locator NA Nb of data = 500 Nb of active values = 500 Minimum value = 0.000 Maximum value = 1.000 Mean value = 0.186 Standard Deviation = 0.389 Variance = 0.151 Variables --------- Column = 0 - Name = rank - Locator = NA Column = 1 - Name = x-1 - Locator = x1 Column = 2 - Name = x-2 - Locator = x2 Column = 3 - Name = sel - Locator = NA
In [7]:
res = gp.symbol(mydb, nameColor="sel")
Extracting a new Data Base upon ranks¶
We demonstrate the possibility to extract a Data Base by specifying the selected ranks of an Input Data Base.
In [8]:
ranks = gl.VectorHelper.sampleRanks(mydb.getNSample(), proportion=0.2)
print("Number of selected samples =", len(ranks))
Number of selected samples = 100
In [9]:
mydbred1 = gl.Db.createReduce(mydb, ranks=ranks)
In [10]:
gp.symbol(mydbred1)
gp.decoration(title="Extraction by Ranks")
Extracting a new Data Base upon selection¶
We now create turn the variable 'sel' into a selection and createa new data set which is restricted to the only active samples
In [11]:
mydb.setLocator("sel", gl.ELoc.SEL)
mydbred2 = gl.Db.createReduce(mydb)
mydbred2
Out[11]:
Data Base Characteristics ========================= Data Base Summary ----------------- File is organized as a set of isolated points Space dimension = 2 Number of Columns = 4 Total number of samples = 93 Number of active samples = 93 Variables --------- Column = 0 - Name = rank - Locator = NA Column = 1 - Name = x-1 - Locator = x1 Column = 2 - Name = x-2 - Locator = x2 Column = 3 - Name = sel - Locator = sel
In [12]:
ax = gp.plot(mydbred2)
gp.decoration(title="Extraction by Selection")
Defining a Line Data set¶
The data is defined in 2-D as a set of lines at random. The number of lines is provided. Each line contains a number of samples drawn at random.
In [13]:
mydb = gl.DbLine.createFillRandom(ndim=2, nbline=10, nperline=30, delta=[1, -1])
Understanding the contents of the DbLine file created randomly
In [14]:
mydb.display()
Data Base Line Characteristics ============================== Number of Lines = 10 Number of samples = 274 Line length = 24 / 29 / 30 / 26 / 26 / 22 / 23 / 35 / 23 / 36 Variables --------- Column = 0 - Name = rank - Locator = NA Column = 1 - Name = x-1 - Locator = x1 Column = 2 - Name = x-2 - Locator = x2
Displaying the Line Data set
In [15]:
res = gp.line(mydb, flagSample=True, flagAnnotateHeader=True)
Defining an Oriented Graph Data Set¶
The data is defined in 2-D as a set of samples which are joined by arcs in order to form a Graph.
In [16]:
x1 = np.array(
[
0.0,
1.0,
2.0,
3.0,
4.0,
5.0,
6.0,
2.0,
3.0,
4.0,
5.0,
6.0,
7.0,
3.0,
4.0,
2.0,
3.0,
4.0,
0.0,
5.0,
7.0,
]
)
x2 = np.array(
[
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
2.0,
2.0,
3.0,
3.0,
3.0,
4.0,
5.0,
4.0,
]
)
z1 = np.array(
[
1.2,
2.5,
3.6,
1.4,
0.3,
0.2,
8.2,
0.3,
3.2,
1.2,
0.4,
0.1,
0.3,
3.2,
4.5,
1.2,
5.2,
1.2,
1.1,
2.2,
3.3,
]
)
tab = np.concatenate((x1, x2, z1))
nech = len(x1)
arcs = gl.MatrixSparse(nech, nech)
arcs.setValue(0, 1, gl.law_uniform())
arcs.setValue(1, 2, gl.law_uniform())
arcs.setValue(2, 3, gl.law_uniform())
arcs.setValue(3, 4, gl.law_uniform())
arcs.setValue(4, 5, gl.law_uniform())
arcs.setValue(5, 6, gl.law_uniform())
arcs.setValue(2, 7, gl.law_uniform())
arcs.setValue(7, 8, gl.law_uniform())
arcs.setValue(8, 9, gl.law_uniform())
arcs.setValue(9, 10, gl.law_uniform())
arcs.setValue(10, 11, gl.law_uniform())
arcs.setValue(11, 12, gl.law_uniform())
arcs.setValue(8, 13, gl.law_uniform())
arcs.setValue(13, 14, gl.law_uniform())
arcs.setValue(14, 11, gl.law_uniform())
arcs.setValue(7, 15, gl.law_uniform())
arcs.setValue(15, 16, gl.law_uniform())
arcs.setValue(16, 17, gl.law_uniform())
dbgraphO = gl.DbGraphO.createFromMatrix(
nech, gl.ELoadBy.COLUMN, tab, arcs, ["x1", "x2", "z1"], ["x1", "x2", "z1"]
)
In [17]:
gl.OptCst.define(gl.ECst.NTROW, -1)
gl.OptCst.define(gl.ECst.NTCOL, -1)
dbgraphO.display()
Data Base Oriented Graph Characteristics
========================================
Variables
---------
Column = 0 - Name = rank - Locator = NA
Column = 1 - Name = x1 - Locator = x1
Column = 2 - Name = x2 - Locator = x2
Column = 3 - Name = z1 - Locator = z1
Data Base Summary
-----------------
File is organized as a set of isolated points
Space dimension = 2
Number of Columns = 4
Total number of samples = 21
- Number of rows = 21
- Number of columns = 21
- Sparse Format
[, 0] [, 1] [, 2] [, 3] [, 4] [, 5] [, 6]
[ 0,] . 0.066 . . . . .
[ 1,] . . 0.956 . . . .
[ 2,] . . . 0.423 . . .
[ 3,] . . . . 0.420 . .
[ 4,] . . . . . 0.064 .
[ 5,] . . . . . . 0.758
[ 6,] . . . . . . .
[ 7,] . . . . . . .
[ 8,] . . . . . . .
[ 9,] . . . . . . .
[ 10,] . . . . . . .
[ 11,] . . . . . . .
[ 12,] . . . . . . .
[ 13,] . . . . . . .
[ 14,] . . . . . . .
[ 15,] . . . . . . .
[ 16,] . . . . . . .
[ 17,] . . . . . . .
[ 18,] . . . . . . .
[ 19,] . . . . . . .
[ 20,] . . . . . . .
[, 7] [, 8] [, 9] [, 10] [, 11] [, 12] [, 13]
[ 0,] . . . . . . .
[ 1,] . . . . . . .
[ 2,] 0.618 . . . . . .
[ 3,] . . . . . . .
[ 4,] . . . . . . .
[ 5,] . . . . . . .
[ 6,] . . . . . . .
[ 7,] . 0.883 . . . . .
[ 8,] . . 0.703 . . . 0.520
[ 9,] . . . 0.864 . . .
[ 10,] . . . . 0.746 . .
[ 11,] . . . . . 0.310 .
[ 12,] . . . . . . .
[ 13,] . . . . . . .
[ 14,] . . . . 0.202 . .
[ 15,] . . . . . . .
[ 16,] . . . . . . .
[ 17,] . . . . . . .
[ 18,] . . . . . . .
[ 19,] . . . . . . .
[ 20,] . . . . . . .
[, 14] [, 15] [, 16] [, 17] [, 18] [, 19] [, 20]
[ 0,] . . . . . . .
[ 1,] . . . . . . .
[ 2,] . . . . . . .
[ 3,] . . . . . . .
[ 4,] . . . . . . .
[ 5,] . . . . . . .
[ 6,] . . . . . . .
[ 7,] . 0.194 . . . . .
[ 8,] . . . . . . .
[ 9,] . . . . . . .
[ 10,] . . . . . . .
[ 11,] . . . . . . .
[ 12,] . . . . . . .
[ 13,] 0.621 . . . . . .
[ 14,] . . . . . . .
[ 15,] . . 0.412 . . . .
[ 16,] . . . 0.221 . . .
[ 17,] . . . . . . .
[ 18,] . . . . . . .
[ 19,] . . . . . . .
[ 20,] . . . . . . .
In [18]:
gp.plot(dbgraphO, flagSample=True, flagAnnotate=True)
gp.symbol(dbgraphO, nameSize="z1")
plt.show()
Defining an Meshing Data Set¶
We first concentrate on the Turbo Meshing based on a regular Grid
Case of Turbo Meshing¶
In [19]:
nx = [12, 15]
dx = [1.3, 1.1]
tab = np.ones(12 * 15)
dbmeshT = gl.DbMeshTurbo(
nx,
dx,
gl.VectorDouble(),
gl.VectorDouble(),
gl.ELoadBy.SAMPLE,
tab,
["var"],
["z1"],
)
dbmeshT
Out[19]:
Data Base for Turbo Meshing =========================== Variables --------- Column = 0 - Name = rank - Locator = NA Column = 1 - Name = var - Locator = z1 Data Base Summary ----------------- File is organized as a regular grid Space dimension = 2 Number of Columns = 2 Total number of samples = 180 Turbo Meshing ============= Grid characteristics: --------------------- Origin : 0.000 0.000 Mesh : 1.300 1.100 Number : 12 15 Euclidean Geometry Space Dimension = 2 Number of Apices per Mesh = 3 Number of Meshes = 308 Number of Apices = 180 Bounding Box Extension ---------------------- Dim #1 - Min:0 - Max:14.3 Dim #2 - Min:0 - Max:15.4
In [20]:
res = gp.mesh(dbmeshT, flagApex=True)
The next chunk is meant to demonstrate that the 'DbMesh' can be used as a standard 'DbGrid', in particular for adding new fields to the Data Base.
In [21]:
dbmeshT.addColumnsByConstant(1, 5.0, "NewVar", gl.ELoc.V)
dbmeshT
Out[21]:
Data Base for Turbo Meshing =========================== Variables --------- Column = 0 - Name = rank - Locator = NA Column = 1 - Name = var - Locator = z1 Column = 2 - Name = NewVar - Locator = v1 Data Base Summary ----------------- File is organized as a regular grid Space dimension = 2 Number of Columns = 3 Total number of samples = 180 Turbo Meshing ============= Grid characteristics: --------------------- Origin : 0.000 0.000 Mesh : 1.300 1.100 Number : 12 15 Euclidean Geometry Space Dimension = 2 Number of Apices per Mesh = 3 Number of Meshes = 308 Number of Apices = 180 Bounding Box Extension ---------------------- Dim #1 - Min:0 - Max:14.3 Dim #2 - Min:0 - Max:15.4
Case of Standard Meshing¶
In [22]:
x1 = np.array([0.0, 1.0, 1.0, 2.0, 3.0, 4.0, 5.0])
x2 = np.array([0.0, 0.0, 2.0, 2.0, 1.0, 2.0, 1.0])
apices = np.concatenate((x1, x2))
i1 = np.array([0, 1, 1, 3, 4, 1])
i2 = np.array([1, 2, 3, 4, 5, 4])
i3 = np.array([2, 3, 4, 5, 6, 6])
meshes = np.concatenate((i1, i2, i3))
In [23]:
dbmeshS = gl.DbMeshStandard.create(ndim=2, napexpermesh=3, apices=apices, meshes=meshes)
dbmeshS
Out[23]:
Data Base for Standard Meshing ============================== Variables --------- Column = 0 - Name = x-1 - Locator = x1 Column = 1 - Name = x-2 - Locator = x2 Data Base Summary ----------------- File is organized as a set of isolated points Space dimension = 2 Number of Columns = 2 Total number of samples = 7 Standard Meshing ================ Euclidean Geometry Space Dimension = 2 Number of Apices per Mesh = 3 Number of Meshes = 6 Number of Apices = 7 Bounding Box Extension ---------------------- Dim #1 - Min:0 - Max:5 Dim #2 - Min:0 - Max:2
In [24]:
res = gp.mesh(dbmeshS, flagApex=True)
