# on 13-Nov-2019 (Wed)

#### Annotation 4536875224332

 Existe uma trindade sagrada da segurança da informação. São três princípios ou propriedades: Confidencialidade, Integridade e Disponibilidade – conhecidos como CID. Se um ou mais desses princípios forem desrespeitados em algum momento, significa que houve um incidente de segurança da informação.

#### pdf

cannot see any pdfs

#### Flashcard 4536877583628

Question
Existe uma trindade sagrada da segurança da informação. São três princípios ou propriedades, quais são elas?(novo com stilo small).
Confidencialidade, Integridade e Disponibilidade – conhecidos como CID. Se um ou mais desses princípios forem desrespeitados em algum momento, significa que houve um incidente de segurança da informação.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Annotation 4538407456012

 Connection string portability In some circumstances, we might need to create several QVW files for extracting several tables from a particular database. An elegant and administration-friendly approach is to store the connection string in a text file, residing in a folder that is reachable from your QVW files. Import this connection into every QVW via an include statement (from the Edit Script window, select Insert | Include Statement). The benefit of this approach is that if the connection string should change, you only need to modify it in one place, and all of the corresponding QVW files will automatically use the updated Connect statement.

#### pdf

cannot see any pdfs

#### Flashcard 4538409291020

Question
One category of statistical dimension reduction techniques is commonly called *** (PCA) or the *** (SVD).
One category of statistical dimension reduction techniques is commonly called principal components analysis (PCA) or the singular value decomposition (SVD).

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538411388172

Question
One category of statistical dimension reduction techniques is commonly called principal components analysis (PCA) or the singular value decomposition (SVD). These techniques generally are applied in situations where the rows of a matrix represent *** of some sort and the columns of the matrix represent *** or *** (but this is by no means a ***).
One category of statistical dimension reduction techniques is commonly called principal components analysis (PCA) or the singular value decomposition (SVD). These techniques generally are applied in situations where the rows of a matrix represent observations of some sort and the columns of the matrix represent features or variables (but this is by no means a requirement).

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538413485324

Question
One category of statistical dimension reduction techniques is commonly called principal components analysis (PCA) or the singular value decomposition (SVD). These techniques generally are applied in situations where the *** of a matrix represent observations of some sort and the *** of the matrix represent features or variables (but this is by no means a ***).
One category of statistical dimension reduction techniques is commonly called principal components analysis (PCA) or the singular value decomposition (SVD). These techniques generally are applied in situations where the rows of a matrix represent observations of some sort and the columns of the matrix represent features or variables (but this is by no means a requirement).

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538415582476

Question
In an abstract sense, the SVD or PCA can be thought of as a way to approximate a ***-dimensional matrix (i.e. a high number of ***) with a a few ***-dimensional matrices.
In an abstract sense, the SVD or PCA can be thought of as a way to approximate a high-dimensional matrix (i.e. a large number of columns) with a a few low-dimensional matrices.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538417679628

Question
In an abstract sense, the SVD or PCA can be thought of as a way to approximate a high-dimensional *** with a a few low-dimensional ***.
In an abstract sense, the SVD or PCA can be thought of as a way to approximate a high-dimensional matrix with a a few low-dimensional matrices.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538419776780

Question
there’s a bit of data *** angle to SVD or PCA.
there’s a bit of data compression angle to SVD or PCA.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538421873932

Question
When confronted with matrix data a quick and easy thing to organize the data a bit is to apply an *** algorithm to it.
When confronted with matrix data a quick and easy thing to organize the data a bit is to apply an hierarchical clustering algorithm to it.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538423971084

Question
When confronted with matrix data a quick and easy thing to organize the data a bit is to apply an hierarchical clustering algorithm to it. Such a clustering can be visualized with the ***() function in R.
When confronted with matrix data a quick and easy thing to organize the data a bit is to apply an hierarchical clustering algorithm to it. Such a clustering can be visualized with the heatmap() function in R.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538426068236

Question

find the best matrix created with fewer variables (lower rank) that explains the original data.

this goal could be characterized as *** data compression.

find the best matrix created with fewer variables (lower rank) that explains the original data.

this goal could be characterized as lossy data compression.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538428165388

Question

find the best matrix created with fewer variables (lower rank) that explains the original data.

this goal could be characterized as lossy ***.

find the best matrix created with fewer variables (lower rank) that explains the original data.

this goal could be characterized as lossy data compression.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538430262540

Question
when comparing two matrices, the one with *** has lower rank.
when comparing two matrices, the one with less variables has lower rank.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538432359692

Question
when comparing two matrices, the one with less variables has lower ***.
when comparing two matrices, the one with less variables has lower rank.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538434456844

Question

If X is a matrix with each variable in a column and each observation in a row,

then the *** is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538436553996

Question

If X is a matrix with each *** in a column and each *** in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538438651148

Question

If X is a matrix with each variable in a *** and each observation in a ***,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538440748300

Question

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

*** = ***

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538442845452

Question

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

where the columns of *** (left singular vectors) are orthogonal, the columns of *** (right singular vectors) are orthogonal and *** is a diagonal matrix of singular values.

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

where the columns of U (left singular vectors) are orthogonal, the columns of $V$ (right singular vectors) are orthogonal and $D$ is a diagonal matrix of singular values.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538444942604

Question

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

where the columns of U (left *** vectors) are orthogonal, the columns of $V$ (right *** vectors) are orthogonal and $D$ is a diagonal matrix of *** values.

[default - edit me]

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538447039756

Question

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

where the columns of U (left singular ***) are orthogonal, the columns of $V$ (right singular ***) are orthogonal and $D$ is a diagonal matrix of singular ***.

[default - edit me]

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538449136908

Question

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

where the columns of U (left singular vectors) are ***, the columns of $V$ (right singular vectors) are *** and $D$ is a *** of singular values.

If X is a matrix with each variable in a column and each observation in a row,

then the SVD is a matrix decomposition that represents X as a matrix product of three matrices:

X = U DV ′

where the columns of U (left singular vectors) are orthogonal, the columns of $V$ (right singular vectors) are orthogonal and $D$ is a diagonal matrix of singular values.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538451234060

Question
Principal components analysis is simply an application of the ***.
Principal components analysis is simply an application of the SVD.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538453331212

Question
The principal components are equal to the *** values if you first scale the data by subtracting the *** and dividing each *** by its ***.
The principal components are equal to the right singular values if you first scale the data by subtracting the column mean and dividing each column by its standard deviation.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538455428364

Question
The principal components are equal to the right singular values if you first *** the data by *** the column mean and *** each column by its standard deviation.
The principal components are equal to the right singular values if you first scale the data by subtracting the column mean and dividing each column by its standard deviation.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538457525516

Question
The principal components are equal to the right singular values if you first scale the data by subtracting the column mean and dividing each column by its standard deviation (that can be done with the ***() function in R).
The principal components are equal to the right singular values if you first scale the data by subtracting the column mean and dividing each column by its standard deviation (that can be done with the scale() function in R).

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538459622668

Question
The SVD can be computed in R using the ***() function.
The SVD can be computed in R using the svd() function.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538461719820

Question
The svd() function in R returns a list containing three components named ***, ***, and ***.
The svd() function in R returns a list containing three components named u, d, and v.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538463816972

Question

The svd() function in R returns a list containing three components named u, d, and v.

The *** components correspond to the matrices of left and right singular vectors, respectively, while the *** component is a vector of singular values, corresponding to the diagonal of the matrix ***

The svd() function in R returns a list containing three components named u, d, and v.

The u and v components correspond to the matrices of left and right singular vectors, respectively, while the d component is a vector of singular values, corresponding to the diagonal of the matrix D

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538465914124

Question

The svd() function in R returns a list containing three components named u, d, and v.

The u and v components correspond to the matrices of ***, respectively, while the d component is a vector of ***, corresponding to the *** of the matrix D

The svd() function in R returns a list containing three components named u, d, and v.

The u and v components correspond to the matrices of left and right singular vectors, respectively, while the d component is a vector of singular values, corresponding to the diagonal of the matrix D

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538468011276

Question
The singular values produced by the svd() in R are in order from *** to ***.
The singular values produced by the svd() in R are in order from largest to smallest.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538470108428

Question
The singular values produced by the svd() in R are in order from largest to smallest and when *** are proportional the amount of variance explained by a given singular vector.
The singular values produced by the svd() in R are in order from largest to smallest and when squared are proportional the amount of variance explained by a given singular vector.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538472205580

Question
The singular values produced by the svd() in R are in order from largest to smallest and when squared are proportional the amount of *** explained by a given ***.
The singular values produced by the svd() in R are in order from largest to smallest and when squared are proportional the amount of variance explained by a given singular vector.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538474302732

Question
PCA can be applied to the data by calling the ***() function in R.
PCA can be applied to the data by calling the prcomp() function in R.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538476399884

Question

Whether you call a procedure SVD or PCA really just depends on who you talk to.

*** and people with that kind of background will typically call it PCA while *** and *** will tend to call it SVD.

Whether you call a procedure SVD or PCA really just depends on who you talk to.

Statisticians and people with that kind of background will typically call it PCA while engineers and mathematicians will tend to call it SVD.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538478497036

Question

Whether you call a procedure SVD or PCA really just depends on who you talk to.

Statisticians and people with that kind of background will typically call it *** while engineers and mathematicians will tend to call it ***.

Whether you call a procedure SVD or PCA really just depends on who you talk to.

Statisticians and people with that kind of background will typically call it PCA while engineers and mathematicians will tend to call it SVD.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Flashcard 4538480594188

Question
Most SVD and PCA routines simply cannot be applied if there are *** in the dataset.
Most SVD and PCA routines simply cannot be applied if there are missing values in the dataset.

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Annotation 4538482691340

 In the event of missing data, there are typically a series of questions that should be asked: • Determine the reason for the missing data; what is the process that lead to the data being missing? • Is the proportion of missing values so high as to invalidate any sort of analysis? • Is there information in the dataset that would allow you to predict/infer the values of the missing data?

#### pdf

cannot see any pdfs

#### Flashcard 4538485050636

Question
The impute package in R is available from the *** project.