W |
Date |
Due (before class @ 3:30pm)
| Topics
Tools |
#To-do / Homework Project |
1 |
8/29 (T) |
|
|
[slides] Course introduction, setup
|
8/31 (Th) |
#1 |
|
[slides] Data in linguistics
|
2 |
9/5 (T) |
|
HW1: Explore linguistic data |
[slides] Data in linguistics, processing data
|
9/7 (Th) |
#2 |
|
Data processing fundamentals |
[slides] Python's numpy library |
3 |
9/12 (T) |
#3 |
|
[slides] Data frames with pandas |
9/14 (Th) |
#4 |
|
[slides, JNB] More pandas
|
4 |
9/19 (T) |
#5 |
|
[JNB] Basic text processing |
9/21 (Th) |
|
HW2: Process ETS corpus |
[JNB] Putting it all together, visualization
|
5 |
9/26 (T) |
#6 |
|
[JNB] Group-by, pivoting, visualization |
9/28 (Th) |
#7 |
|
Corpus linguistics |
[slides] Overview & concepts, building & processing |
6 |
10/3 (T) |
|
|
[slides] Data standards & exchange formats: TEI, XML, CSV, JSON |
10/5 (Th) |
#8 |
|
Data mining |
[slides] Data-mining web & social media |
7 |
No class: Monday class held (Fall Break) |
10/12 (Th) |
|
|
Data mining and machine learning |
[JNB] Classifiers |
8 |
10/17 (T) |
#9 |
|
Classifiers continued |
10/19 (Th) |
|
|
[JNB] [JNB] Clustering, feature engineering |
9 |
10/24 (T) |
|
|
Open access & data publishing Guest speaker Lauren Collister [slides] |
10/26 (Th) |
|
HW3: Data Mining & ML |
Machine learning |
[JNB] Homework 3 review |
10 |
10/31 (T) |
|
|
Big data |
[JNB] [slides] HW3 continued |
11/2 (Th) |
|
|
[slides] Bash and command line |
11 |
11/7 (T) |
#10 |
|
[slides] Shell scripting, SSH, supercomputing at CRC |
11/9 (Th) |
#11 |
|
[slides] Guest presentation by Barry Moore II, CRC |
12 |
11/14 (T) |
|
HW4: Supercomputing Big Data |
[slides] Super-computing, computational efficiency |
11/16 (Th) |
#12 |
|
Linguistic annotation, Speech data |
[slides] Linguistic annotation |
13 |
11/21 (T) |
#13 |
|
[slides] Linguistic annotation, continued
|
No class: Thanksgiving break |
14 |
11/28 (T) |
|
|
Project presentations |
11/30 (Th) |
|
|
15 |
12/5 (T) |
|
|
12/7 (Th) |
|
|
16 |
12/14 (Th) |
|
|
Finals week |
*Class schedule is subject to revision throughout the semester.
|