ABT 182 midterm

Which of the following is NOT a useful command when you want to explore your dataframe (named df).

A. df.unique()

Commands to explore dataframe

B. df.info() C. df.describe() D. df.shape() E. df.head()

Keywords in decision making

B. if C. else D. elif

What is the output of the following code?

Color_List = ["blue", "green", "black", "yellow"] Color_List.append("red") print(Color_List) : ['blue', 'green', 'black', 'yellow', 'red']

Which of the following data type is not among sequence types?

Dictionary (dict)

Is the proximity method (aka Thiessen polygons) an exact or inexact interpolation technique?

Discuss your reasons. Exact method, because it produces values exactly equal to observed values at all measurement locations.

You can concatenate the number literal 100 with the string literal "meters" with the following code 100 + "meters"

False

Python integrates modules and packages to provide numerous tools for working with data

Provide the name of a few packages in Python used for spatial analysis. • ArcPy • GeoPandas • Rasterio • Fiona • Shapely

Running the following script returns an error before it begins to execute. Which answer best describes the reason for the error? import arcpy fc = r"C

\Data\Roads arcpy.Buffer_analysis (fc, fc + "_buff", "500 feet") : The path for fc requires a closing quotation mark.

If a=10 and b=5, then which of the following conditional statement is False?

a\\b==0

Choose the correct syntax to return the first row in a Pandas DataFrame

df.loc[0]

Which of the following statements is NOT valid?

if a = b:

Which best describes a tuple?

immutable

If my_list = [24, 19, 27, 41, 34], which of the following returns the third element of the list (27)?

my_list[2]

What is the output of the following code?

var = "ABT182 " * 1 * 3 print(var) : ABT182 ABT182 ABT182

How the weights in kriging technique are calculated?

• Based on semivariogram (not inverse distance)

Give one example of a data type, statement and function

• Data type: list, tuple • Statement: IF ELSE statements • Function: PRINT

Why might Empirical Bayesian Kriging provide more accurate predictions and standard errors than kriging?

• Empirical Bayesian Kriging accounts for uncertainty in the semivariogram, resulting in more accurate prediction than kriging.

What is the main difference between the empirical Bayesian kriging (EBK) and other kriging methods like ordinary and universal kriging?

• Empirical Bayesian Kriging accounts for uncertainty in the semivariogram, resulting in more accurate prediction than kriging. Other kriging methods calculate the semivariogram from known data locations and use this single semivariogram to make predictions at unknown locations. Therefore, they underestimate the standard errors of prediction.

Describe the major assumptions in geostatistical interpolation

• Normally distributed: the distribution should be like a bell-shaped or Gaussian curve • Stationarity: means that statistical properties of the sample data, such as the mean and data variance remain constant regardless of locations. Spatial variability of the data should be the same across the whole study area. • No trends: (no global trends in the sample locations). A trends indicates that the data varies differently at different locations systematically which breaks the stationarity assumption.

What are the advantages of Python compared to other GIS software?

• Python is a free scripting language • Automating repetitive tasks • Simple development environment • Scalability (Writing python scripts is relatively simple) • Integrated modules and packages • Python works on different platforms (Windows, Mac, Linux, Raspberry Pi, etc). • Python can be used to handle big data and perform complex mathematics.

What are different types of sampling and describe one of them?

• Systematic sampling pattern • Random sampling • Cluster sampling • Adaptive sampling

Describe how ordinary kriging generates a prediction surface

• The spatial structure of the sample points is modeled by fitting a function (semivariogram model) to the average empirical semivariances. • For each prediction location, nearby sample measured points are identified as neighbors based on specified search criteria. • New values are predicted for a phenomenon using the semivariogram model (to calculate the weights for neighbors) and neighboring sample points.