Poll Results: Top Languages for Data Mining/Analytics

R (used by 45%), SQL (32%), and Python (25%) are top languages for data mining/data analysis. A typical data miner uses 2 languages.

---

The previous KDnuggets Poll asked What programming languages you used for data mining / data analysis in the past 12 months?

Here are the results, based on 570 voters:

R (257)	45%
SQL (184)	32%
Python (140)	25%
Java (139)	24%
SAS (121)	21%
MATLAB (83)	15%
C/C++ (73)	13%
Unix shell/awk/gawk/sed (59)	10%
Perl (45)	7.9%
Hadoop/Pig/Hive (35)	6.1%
Lisp (4)	0.7%
Other (70)	12.0%
None (7)	1.2%

Notes
Among the top 5 languages, only about 15-25% were used alone.

• 43.2% of voters used 1 language
• 24.9% used 2 languages
• 17.4% used 3 languages
• 8.4% used 4 languages
• 6.1% used 5 or more languages

On average, data miners used 2.1 languages.

The breakdown by region is:

• US/Canada, 42%
• Europe, 30%
• Asia, 16%
• Latin America, 4.9%
• AU/NZ, 2.8%
• Africa/MidEast, 3.0%