klahrich

klahrich

from glob import glob

# Step 1: export to hdf5 chunks
for i, chunk in enumerate([pd.read_csv(file) for file in glob('folder/path')]):
  df_chunk = vaex.from_pandas(chunk, copy_index=False)
  df_chunk.export_hdf5(f'bigfile_part_{i}.hdf5')
  
df = vaex.open('bigfile_part_*.hdf5')

# Step 2: Combine back into one big hdf5 file

klahrich

# Step 1: export to hdf5 chunks
for i, chunk in enumerate(pd.read_csv('bigfile.csv', chunksize=1_000_000)):
  df_chunk = vaex.from_pandas(chunk, copy_index=False)
  df_chunk.export_hdf5(f'bigfile_part_{i}.hdf5')
  
df = vaex.open('bigfile_part_*.hdf5')

# Step 2: Combine back into one big hdf5 file
df.export_hdf5('bigfile.hdf5')

klahrich

" enable syntax highlighting
syntax enable

" show line numbers
set number

" set tabs to have 4 spaces
set ts=4

" indent when moving to the next line while writing code

klahrich

def pi():
    # Number of darts that land inside.
    inside = 0
    # Total number of darts to throw.
    total = 1000000

    # Iterate for the number of darts.
    for i in range(0, total):
        inside += is_inside()
            

klahrich

import math as m

def is_inside():
    x2 = r.random()**2
    y2 = r.random()**2
    
    # Increment if inside unit circle.
    if m.sqrt(x2 + y2) < 1.0:
        return 1
    else:

klahrich

# Challenge no 2: you have a list of names, and you want to find out which names are both long AND have a high percentage of vowels in them.

names = ['Maria', 'Leila', 'Karim', 'Jon', "Kalimero", "John", "Armstrong", "Braztchniev", "Mougandae"]

name_lengths = [len(w) for w in names]
relative_lengths = [l / max(lengths) for l in name_lengths]

vowel_counts = [sum([Counter(name)[v] for v in "aoeui"]) for name in names]
vowel_perc = [vc / l for vc, l in zip(vowel_counts, name_lengths)]

klahrich

# Challenge no 1: you have a list of sentences. What are the top-3 most frequent words (case-insensitive) longer than 3 characters.

from collections import Counter

sentences = ["This is the first sentence", "My first time was in Havana", "What is it this time", "Time is precious"]

words = [word.lower() for sentence in sentences for word in sentence.split()]
counter = Counter([word for word in words if len(word) >= 3])

counter.most_common(3)

klahrich

from pyo import *

s = Server().boot()

# downloaded from sampleswap
first = 'boomy-dirty-kick.wav'
second = 'CP_set1.wav'
third = 'bunchakiks17.wav'

tab1 = SndTable(first)

klahrich

from pyo import *

s = Server().boot()

# Drops the gain 
s.amp = 0.1

# Ramp up of amplitude. From 0.0 to 1.0 in 2 seconds
amp = SigTo(value=1, time=2.0, init=0.0)