Data and analytics Exam 2

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/28

encourage image

There's no tags or description

Looks like no tags are added yet.

29 Terms

1
New cards

message = "I love data analytics courses!" … message[0:2]

characters from position 0 (included) to 2 (excluded) — ’I ’

2
New cards

message = "I love data analytics courses!" … message[2:]

characters from position 2 (included) to the end — ’love data analytics course!’

3
New cards

message = "I love data analytics courses!" … message[:3]

characters from beginning (position 0) to position 3 (excluded) — ’I l'

4
New cards

Lists

fruits = ['apple', ‘banana', 'pineapple', 'mango’]

5
New cards

Sets

Specified by curly braces Set cannot hold duplicate values (will drop any duplicate values)

6
New cards

Dictionaries

Stores value w key value pair (a_dict = {"a":1, "b":2, "c":3, "d": “f”})

7
New cards

check if “b” key exists in a dictionary

'b' in a_dict (returns true/false. Based on the key! Not the value of a key!!!!)

8
New cards

Dictionaries of lists

dol = {"list1":[1, 2, 3], "list2":[4, 5, 6, 7]}

9
New cards

List Of Dictionaries

lod = [{"first":"Jae", "last":"Jung"},

{"first":"Jeremy", "last":"Shafer"}]

10
New cards
Structured
Organized according to a formal data model (i.e., relational schema)
11
New cards
Semi-structured data
No formal data model, but contains symbols to separate and label data elements (CSV, XML, or JSON)
12
New cards
CSV
Each value is separated by a comma
13
New cards
XML
Uses text for values between tags(<tag>”data”</tag>)
14
New cards
JSON
Uses key-value pairs (“key”: “value”)
15
New cards
JSON Object
“key”: {“key”: “value”, “key”: “value”}
16
New cards
JSON Array
“key”: [“value1”, “value1”]
17
New cards
Unstructured data
No data model and no pre-defined organization.
18
New cards
What is ETL and why is it necessary?
Combines data from multiple data sources into a single, consistent data source with a common field
19
New cards
Extract
gets data from the transactional databases
20
New cards
Transform
data into an analysis-ready format (This can include removing duplicates, correcting errors, or combining data.)
21
New cards
Load
data placed into the analytical data store (where it can be analyzed)
22
New cards

Steps of Hypothesis testing

  1. State Null Hypothesis (no relationship between variables)

  2. State Alternative Hypothesis (There is a relationship between variables

  3. Collect Samples

  4. Calculate the test statistics and p-values

  5. Decision rule for rejection of the Null hypothesis (using p-values)


23
New cards
P-value
Probability that the null hypothesis is true
24
New cards
A small p-value ( typically ≤ .05 )
indicates strong evidence against the null hypothesis. So the alternative hypothesis is true. (reject the null hypothesis, there is a statistically significant difference between variables)
25
New cards
A large p-value ( typically > .05 )
indicates weak evidence against the null hypothesis. So the alternative hypothesis is false. (fail to reject the null hypothesis, no statistically significant difference between variables)
26
New cards
Three principles of data visualization
Tell a story, Graphical integrity (lie factor), minimize graphical complexity (data ink, chartjunk, Moiré effects )
27
New cards
Tell a story principle
Label vertical axis and add horizontal lines (We don’t know the units. Because there are many states to compare, horizontal lines may be helpful)
28
New cards
Principles of graphical integrity
lie factors based on exaggerated/understated relationships! 3D charts make it difficult to compare sizes(The size of effect shown in graphic and size of effect in data should be about the same)
29
New cards
Principles of graphical complexity
Data ink (the less complex the better) and Chart Junk (unnecessary info in a chart)