How to find Run length encoding in python - python

I have an array ar = [2,2,2,1,1,2,2,3,3,3,3].
For this array, I want to find the lengths of consecutive same numbers like:
values: 2, 1, 2, 3
lengths: 3, 2, 2, 4
In R, this is obtained by using rle() function. Is there any existing function in python which provides required output?

You can do this with groupby
from itertools import groupby
ar = [2,2,2,1,1,2,2,3,3,3,3]
print([(k, sum(1 for i in g)) for k,g in groupby(ar)])
# [(2, 3), (1, 2), (2, 2), (3, 4)]

Here is an answer for pure numpy:
import numpy as np
def find_runs(x):
"""Find runs of consecutive items in an array."""
# ensure array
x = np.asanyarray(x)
if x.ndim != 1:
raise ValueError('only 1D array supported')
n = x.shape[0]
# handle empty array
if n == 0:
return np.array([]), np.array([]), np.array([])
else:
# find run starts
loc_run_start = np.empty(n, dtype=bool)
loc_run_start[0] = True
np.not_equal(x[:-1], x[1:], out=loc_run_start[1:])
run_starts = np.nonzero(loc_run_start)[0]
# find run values
run_values = x[loc_run_start]
# find run lengths
run_lengths = np.diff(np.append(run_starts, n))
return run_values, run_starts, run_lengths
Credit goes to https://github.com/alimanfoo

Here is an answer using the high-performance pyrle library for run length arithmetic:
# pip install pyrle
# (pyrle >= 0.0.25)
from pyrle import Rle
v = [2,2,2,1,1,2,2,3,3,3,3]
r = Rle(v)
print(r)
# +--------+-----+-----+-----+-----+
# | Runs | 3 | 2 | 2 | 4 |
# |--------+-----+-----+-----+-----|
# | Values | 2 | 1 | 2 | 3 |
# +--------+-----+-----+-----+-----+
# Rle of length 11 containing 4 elements
print(r[4])
# 1.0
print(r[4:7])
# +--------+-----+-----+
# | Runs | 1 | 2 |
# |--------+-----+-----|
# | Values | 1.0 | 2.0 |
# +--------+-----+-----+
# Rle of length 3 containing 2 elements
r + r + 0.5
# +--------+-----+-----+-----+-----+
# | Runs | 3 | 2 | 2 | 4 |
# |--------+-----+-----+-----+-----|
# | Values | 4.5 | 2.5 | 4.5 | 6.5 |
# +--------+-----+-----+-----+-----+
# Rle of length 11 containing 4 elements

Here is an optimized answer using numpy arrays which runs quickly if the run lengths are long.
In this case I want to encode an array of uint16 that can be much
larger than 2**16 using 16 bit unsigned integer run length encoding.
To allow this the array is "chunked" so the indices never exceed
2**16:
import numpy as np
def run_length_encode(array, chunksize=((1 << 16) - 1), dtype=np.int16):
"Chunked run length encoding for very large arrays containing smallish values."
shape = array.shape
ravelled = array.ravel()
length = len(ravelled)
chunk_cursor = 0
runlength_chunks = []
while chunk_cursor < length:
chunk_end = chunk_cursor + chunksize
chunk = ravelled[chunk_cursor : chunk_end]
chunk_length = len(chunk)
change = (chunk[:-1] != chunk[1:])
change_indices = np.nonzero(change)[0]
nchanges = len(change_indices)
cursor = 0
runlengths = np.zeros((nchanges + 1, 2), dtype=dtype)
for (count, index) in enumerate(change_indices):
next_cursor = index + 1
runlengths[count, 0] = chunk[cursor] # value
runlengths[count, 1] = next_cursor - cursor # run length
cursor = next_cursor
# last run
runlengths[nchanges, 0] = chunk[cursor]
runlengths[nchanges, 1] = chunk_length - cursor
runlength_chunks.append(runlengths)
chunk_cursor = chunk_end
all_runlengths = np.vstack(runlength_chunks).astype(dtype)
description = dict(
shape=shape,
runlengths=all_runlengths,
dtype=dtype,
)
return description
def run_length_decode(description):
dtype = description["dtype"]
runlengths = description["runlengths"]
shape = description["shape"]
array = np.zeros(shape, dtype=dtype)
ravelled = array.ravel()
cursor = 0
for (value, size) in runlengths:
run_end = cursor + size
ravelled[cursor : run_end] = value
cursor = run_end
array = ravelled.reshape(shape) # redundant?
return array
def testing():
A = np.zeros((50,), dtype=np.uint16)
A[20:30] = 10
A[30:35] = 6
A[40:] = 3
test = run_length_encode(A, chunksize=17)
B = run_length_decode(test)
assert np.alltrue(A == B)
print ("ok!")
if __name__=="__main__":
testing()
I built this for a project having to do with classifying
microscopy images of mouse embryos.
https://github.com/flatironinstitute/mouse_embryo_labeller
Note: I edited the entry after I found I had to caste the type
in this line to it to work for large arrays:
all_runlengths = np.vstack(runlength_chunks).astype(dtype)

Related

How to efficiently read the array columns in the tsv file into a single npz files for each column efficiently?

I've a data file that looks like this:
58f0965a62d62099f5c0771d35dbc218 0.868632614612579 [0.028979932889342308, 0.004080114420503378, 0.03757167607545853] [-0.006008833646774292, -0.010409083217382431, 0.01565541699528694]
36f7859ce47417470bc28384694f0ac4 0.835115909576416 [0.026130573824048042, -0.00358427781611681, 0.06635218113660812] [-0.06970945745706558, 0.03816794604063034, 0.03491008281707764]
59f7d617bb662155b0d49ce3f27093ed 0.907200276851654 [0.009903069585561752, -0.009721670299768448, 0.0151780480518937] [-0.03264783322811127, 0.0035394825972616673, -0.05089104175567627]
where the columns are respectively
an md5 hash of the data point
a target float output
an array of floats that I want to read into a np.array object
another array of floats that I want to read into a np.array object
I've been reading the file as such to create a numpy array files for the two matrices of array of floats:
import numpy as np
from tqdm import tqdm
import pandas as pd
lol = []
with open('data.tsv') as fin:
for line in tqdm(fin):
md5hash, score, vector1, vector2 = line.strip().split('\t')
row = {'md5_hash': md5hash, 'score':float(score),
'vector1': np.array(eval(vector1)),
'vector2': np.array(eval(vector2))
}
lol.append(row)
df = pd.DataFrame(lol)
training_vector1 = np.array(list(df['vector1']))
# Save the training vectors.
np.save('vector1.npz', training_vector1)
training_vector2 = np.array(list(df['vector2']))
# Save the training vectors.
np.save('vector1.npz', training_vector2)
While this works for small dataset, the actual dataset has a lot more floats in the arrays and it's close to 200 million rows. Here's a sample of 100 rows https://gist.github.com/1f6f0b2501dc334db1e0038d36452f5d
How to efficiently read the array columns in the tsv file into a single npz files for each column efficiently?
First, a note on the overall problem.
Any approach that loads 200M rows similar to the sample input you provided would require some 1.1 TB of memory.
While this is possible, it is certainly not ideal.
Therefore, I would not recommend going forward with this, but rather look into approaches specifically designed for handling large dataset, e.g. HDF5.
Having said that, the problem at hand is not particular complex, but passing through pandas and eval() is probably neither desirable nor beneficial.
The same could be said for cut pre-processing into CSV files that are only marginally simpler to read.
Assuming that np.save() will be equally fast, regardless of how the array is produced, we could say that the following function replicates well the processing in OP:
def process_tsv_OP(filepath="100-translation.embedded-3.tsv"):
lol = []
with open(filepath, "r") as fin:
for line in fin:
md5hash, score, vector1, vector2 = line.strip().split('\t')
row = {'md5_hash': md5hash, 'score':float(score),
'vector1': np.array(eval(vector1)),
'vector2': np.array(eval(vector2))
}
lol.append(row)
df = pd.DataFrame(lol)
training_vector1 = np.array(list(df['vector1']))
training_vector2 = np.array(list(df['vector2']))
return training_vector1, training_vector2
This can be simplified by avoiding pandas and "evil-eval()" (and a number of copying around in memory):
def text2row(text):
text = text[1:-1]
return [float(x) for x in text.split(',')]
def process_tsv(filepath="100-translation.embedded-3.tsv"):
with open(filepath, "r") as in_file:
v1 = []
v2 = []
for line in in_file:
_, _, text_r1, text_r2 = line.strip().split('\t')
r1 = text2row(text_r1)
r2 = text2row(text_r2)
v1.append(r1)
v2.append(r2)
v1 = np.array(v1)
v2 = np.array(v2)
return v1, v2
It is easy to show that the two produce the same output:
def same_res(x, y):
return all(np.allclose(i, j) for i, j in zip(x, y))
same_res(process_tsv(), process_tsv_OP())
# True
but with substantially different timings:
%timeit process_tsv_OP()
# 1 loop, best of 5: 300 ms per loop
%timeit process_tsv()
# 10 loops, best of 5: 86.1 ms per loop
(on the sample input file obtained with: wget https://gist.githubusercontent.com/alvations/1f6f0b2501dc334db1e0038d36452f5d/raw/ee31c052a4dbda131df182f0237dbe6e5197dff2/100-translation.embedded-3.tsv)
Preprocessing the input with cut does not seem to be that beneficial:
!time cut -f3 100-translation.embedded-3.tsv | rev | cut -c2- | rev | cut -c2- > vector1.csv
# real 0m0.184s
# user 0m0.102s
# sys 0m0.233s
!time cut -f4 100-translation.embedded-3.tsv | rev | cut -c2- | rev | cut -c2- > vector2.csv
# real 0m0.208s
# user 0m0.113s
# sys 0m0.279s
%timeit np.genfromtxt('vector1.csv', delimiter=','); np.genfromtxt('vector2.csv', delimiter=',')
# 1 loop, best of 5: 130 ms per loop
and, while some time may be saved by using pd.read_csv():
%timeit pd.read_csv('vector1.csv').to_numpy(); pd.read_csv('vector2.csv').to_numpy()
# 10 loops, best of 5: 85.7 ms per loop
this seems to be even slower than the original approach on the provided dataset (although cut itself may scale better for larger inputs).
If you really want to stick to the npy file format for this, you may at least wish to append to your output in blocks.
While this is not supported well with NumPy alone, you could use NpyAppendArray (see also here).
The modified process_tsv() would look like:
import os
from npy_append_array import NpyAppendArray
def process_tsv_append(
in_filepath="100-translation.embedded-3.tsv",
out1_filepath="out1.npy",
out2_filepath="out2.npy",
append_every=10,
):
# clear output files
for filepath in (out1_filepath, out2_filepath):
if os.path.isfile(filepath):
os.remove(filepath)
with \
open(in_filepath, "r") as in_file, \
NpyAppendArray(out1_filepath) as npaa1, \
NpyAppendArray(out2_filepath) as npaa2:
v1 = []
v2 = []
for i, line in enumerate(in_file, 1):
_, _, text_r1, text_r2 = line.strip().split("\t")
r1 = text2row(text_r1)
r2 = text2row(text_r2)
v1.append(r1)
v2.append(r2)
if i % append_every == 0:
npaa1.append(np.array(v1))
npaa2.append(np.array(v2))
v1 = []
v2 = []
if len(v1) > 0: # assumes len(v1) == len(v2)
npaa1.append(np.array(v1))
npaa2.append(np.array(v2))
process_tsv_append()
v1 = np.load("out1.npy")
v2 = np.load("out2.npy")
same_res(process_tsv(), (v1, v2))
# True
All this can be speed up relatively blindly with Cython, but the speed-up seems to be marginal:
%%cython -c-O3 -c-march=native -a
#cython: language_level=3, boundscheck=False, wraparound=False, initializedcheck=False, cdivision=True, infer_types=True
import numpy as np
cpdef text2row_cy(text):
return [float(x) for x in text[1:-1].split(',')]
cpdef process_tsv_cy(filepath="100-translation.embedded-3.tsv"):
with open(filepath, "r") as in_file:
v1 = []
v2 = []
for line in in_file:
_, _, text_r1, text_r2 = line.strip().split('\t')
r1 = text2row_cy(text_r1)
r2 = text2row_cy(text_r2)
v1.append(r1)
v2.append(r2)
v1 = np.array(v1)
v2 = np.array(v2)
return v1, v2
print(same_res(process_tsv_cy(), process_tsv_OP()))
# True
%timeit process_tsv_cy()
# 10 loops, best of 5: 72.4 ms per loop
Similarly, pre-allocating the arrays does not seem to be beneficial:
def text2row_out(text, out):
for i, x in enumerate(text[1:-1].split(',')):
out[i] = float(x)
def process_tsv_alloc(filepath="100-translation.embedded-3.tsv"):
num_lines = open(filepath, "r").read().count("\n")
with open(filepath, "r") as in_file:
# num lines
num_lines = in_file.read().count("\n")
# num cols
in_file.seek(0)
line = next(in_file)
_, _, text_r1, text_r2 = line.strip().split('\t')
num_cols1 = len(text_r1.split(","))
num_cols2 = len(text_r2.split(","))
# populate arrays
v1 = np.empty((num_lines, num_cols1))
v2 = np.empty((num_lines, num_cols2))
in_file.seek(0)
for i, line in enumerate(in_file):
_, _, text_r1, text_r2 = line.strip().split('\t')
text2row_out(text_r1, v1[i])
text2row_out(text_r2, v2[i])
return v1, v2
print(same_res(process_tsv_alloc(), process_tsv_OP()))
%timeit process_tsv_alloc()
# 10 loops, best of 5: 110 ms per loop
A significant reduction in the running time can be obtained with Numba (and possibly with Cython too) by rewriting everything to be closer to C. In order to make our code compatible with -- and beneficial to have it accelerated by -- Numba, we need to make significant modifications:
open the file as bytes (no longer supporting UTF-8, which is not a significant issue for the problem at hand)
read and process the file in blocks, which needs to be sufficiently large, say in the order of 1M
write all string handling functions by hand, notably the string-to-float conversion
import numpy as np
import numba as nb
#nb.njit
def bytes2int(text):
c_min = ord("0")
c_max = ord("9")
n = len(text)
valid = n > 0
# determine sign
start = n - 1
stop = -1
sign = 1
if valid:
first = text[0]
if first == ord("+"):
stop = 0
elif first == ord("-"):
sign = -1
stop = 0
# parse rest
number = 0
j = 0
for i in range(start, stop, -1):
c = text[i]
if c_min <= c <= c_max:
number += (c - c_min) * 10 ** j
j += 1
else:
valid = False
break
return sign * number if valid else None
#nb.njit
def bytes2float_helper(text):
sep = ord(".")
c_min = ord("0")
c_max = ord("9")
n = len(text)
valid = n > 0
# determine sign
start = n - 1
stop = -1
sign = 1
if valid:
first = text[0]
if first == ord("+"):
stop = 0
elif first == ord("-"):
sign = -1
stop = 0
# parse rest
sep_pos = 0
number = 0
j = 0
for i in range(start, stop, -1):
c = text[i]
if c_min <= c <= c_max:
number += (c - c_min) * 10 ** j
j += 1
elif c == sep and sep_pos == 0:
sep_pos = j
else:
valid = False
break
return sign * number, sep_pos, valid
#nb.njit
def bytes2float(text):
exp_chars = b"eE"
exp_pos = -1
for exp_char in exp_chars:
for i, c in enumerate(text[::-1]):
if c == exp_char:
exp_pos = i
break
if exp_pos > -1:
break
if exp_pos > 0:
exp_number = bytes2int(text[-exp_pos:])
if exp_number is None:
exp_number = 0
number, sep_pos, valid = bytes2float_helper(text[:-exp_pos-1])
result = number / 10.0 ** (sep_pos - exp_number) if valid else None
else:
number, sep_pos, valid = bytes2float_helper(text)
result = number / 10.0 ** sep_pos if valid else None
return result
#nb.njit
def btrim(text):
space = ord(" ")
tab = ord("\t")
nl = ord("\n")
cr = ord("\r")
start = 0
stop = 0
for c in text:
if c == space or c == tab or c == nl or c == cr:
start += 1
else:
break
for c in text[::-1]:
if c == space:
stop += 1
else:
break
if start == 0 and stop == 0:
return text
elif stop == 0:
return text[start:]
else:
return text[start:-stop]
#nb.njit
def text2row_nb(text, sep, num_cols, out, curr_row):
last_i = 0
j = 0
for i, c in enumerate(text):
if c == sep:
x = bytes2float(btrim(text[last_i:i]))
out[curr_row, j] = x
last_i = i + 2
j += 1
x = bytes2float(btrim(text[last_i:]))
out[curr_row, j] = x
#nb.njit
def process_line(line, psep, sep, num_psep, num_cols1, num_cols2, out1, out2, curr_row):
if len(line) > 0:
psep_pos = np.empty(num_psep, dtype=np.int_)
j = 0
for i, char in enumerate(line):
if char == psep:
psep_pos[j] = i
j += 1
text2row_nb(line[psep_pos[-2] + 2:psep_pos[-1] - 1], sep, num_cols1, out1, curr_row)
text2row_nb(line[psep_pos[-1] + 2:-1], sep, num_cols2, out2, curr_row)
#nb.njit
def decode_block(block, psep, sep, num_lines, num_cols1, num_cols2, out1, out2, curr_row):
nl = ord("\n")
last_i = 0
i = j = 0
for c in block:
if c == nl:
process_line(block[last_i:i], psep, sep, 3, num_cols1, num_cols2, out1, out2, curr_row)
j += 1
last_i = i
curr_row += 1
if j >= num_lines:
break
i += 1
return block[i + 1:], curr_row
#nb.njit
def count_nl(block, start=0):
nl = ord("\n")
for c in block:
if c == nl:
start += 1
return start
def process_tsv_block(filepath="100-translation.embedded-3.tsv", size=2 ** 18):
with open(filepath, "rb") as in_file:
# count newlines
num_lines = 0
while True:
block = in_file.read(size)
if block:
num_lines = count_nl(block, num_lines)
else:
break
# count num columns
in_file.seek(0)
line = next(in_file)
_, _, text_r1, text_r2 = line.strip().split(b'\t')
num_cols1 = len(text_r1.split(b","))
num_cols2 = len(text_r2.split(b","))
# fill output arrays
v1 = np.empty((num_lines, num_cols1))
v2 = np.empty((num_lines, num_cols2))
in_file.seek(0)
remainder = b""
curr_row = 0
while True:
block = in_file.read(size)
if block:
block = remainder + block
num_lines = count_nl(block)
if num_lines > 0:
remainder, curr_row = decode_block(block, ord("\t"), ord(","), num_lines, num_cols1, num_cols2, v1, v2, curr_row)
else:
remainder = block
else:
num_lines = count_nl(remainder)
if num_lines > 0:
remainder, curr_row = decode_block(remainder, ord("\t"), ord(","), num_lines, num_cols1, num_cols2, v1, v2, curr_row)
break
return v1, v2
The prize for all this work is a mere ~2x speed up over process_tsv():
print(same_res(process_tsv_block(), process_tsv_OP()))
# True
%timeit process_tsv_block()
# 10 loops, best of 5: 48.8 ms per loop
Cut the 3rd column, remove the first and last square brackets
cut -f3 data.tsv | rev | cut -c2- | rev | cut -c2- > vector1.csv
Repeat the same for Vector 2
cut -f4 data.tsv | rev | cut -c2- | rev | cut -c2- > vector2.csv
Read the csv into numpy in Python save to npy file.
import numpy as np
np.save('vector1.npy', np.genfromtxt('vector1.csv', delimiter=','))
np.save('vector1.npy', np.genfromtxt('vector2.csv', delimiter=','))
The other answers are good, the version below is a variation that uses dask. Since the original data is in text format, let's use dask.bag API.
First, import modules and define a utility function:
from dask.array import from_delayed, from_npy_stack, to_npy_stack, vstack
from dask.bag import read_text
from numpy import array, nan, stack
def process_line(line):
"""Utility function adapted from the snippet in the question."""
md5hash, score, vector1, vector2 = line.strip().split("\t")
row = {
"md5_hash": md5hash,
"score": float(score),
"vector1": array(eval(vector1)),
"vector2": array(eval(vector2)),
}
return row
Next, create a bag:
bag = read_text("100-translation.embedded-3.tsv", blocksize="1mb").map(process_line)
Since the sample snippet is small, to simulate 'big data', let's pretend that we can load '1mb' at once. This should create 3 partitions in the bag.
Next, isolate the vectors/arrays and convert them to dask.arrays:
# create delayed versions of the arrays
a1 = bag.pluck("vector1").map_partitions(stack).to_delayed()
a2 = bag.pluck("vector2").map_partitions(stack).to_delayed()
# convert the delayed objects to dask array
A1 = vstack(
[from_delayed(a, shape=(nan, 768), dtype="float") for a in a1],
allow_unknown_chunksizes=True,
)
A2 = vstack(
[from_delayed(a, shape=(nan, 768), dtype="float") for a in a2],
allow_unknown_chunksizes=True,
)
Now, we can save the arrays as npy stacks:
to_npy_stack("_A1", A1)
to_npy_stack("_A2", A2)
Note that this processing is not ideal, since the workers will pass over the data twice (once for each array), but with the current API I couldn't think of a better way.
Furthermore, note that the npy stacks preserve the 'unknown' chunks as metadata, even though all the relevant information was computed. This is something that could be improved in dask codebase, but for now the easiest fix is to load the data again, compute chunks, rechunk (to get nice, grid-like structure) and save again:
# rechunk into regular-sized format
A1 = from_npy_stack("_A1")
A1.compute_chunk_sizes()
A1.rechunk(chunks=(40, 768))
to_npy_stack("A1_final", A1)
# rechunk into regular-sized format
A2 = from_npy_stack("_A2")
A2.compute_chunk_sizes()
A2.rechunk(chunks=(40, 768))
to_npy_stack("A2_final", A2)
Of course on the real dataset, you'd want to use bigger chunks. And the final save operation does not have to be to numpy stacks, depending on your interest this could now be stored as HDF5 or zarr array.
If the output format is changed to a raw binary file then the input file can be processed line by line without storing the complete result in RAM.
import numpy as np
fh_in = open('data.tsv')
fh_vec1 = open('vector1.bin', 'wb')
fh_vec2 = open('vector2.bin', 'wb')
linecount = 0
for line in fh_in:
hash_, score, vec1, vec2 = line.strip().split('\t')
np.fromstring(vec1.strip('[]'), sep=',').tofile(fh_vec1)
np.fromstring(vec2.strip('[]'), sep=',').tofile(fh_vec2)
linecount += 1
A raw binary file doesn't store any info about dtype, shape, or byte order.
For loading it back into an array you can use np.fromfile or np.memmap and then call .reshape(linecount, -1) on it.

how to find minimum element of adjacent elements of a position in a matrix

I have a 5x5 matrix and I have to find the minimum of adjacent elements for a position and add that minimum number to that position... this has to be done for all the elements in the matrix except for the 1st row and 1st column.
This is the matrix
A= [[1 1 2 2 3],[1 1 0 1 0],[2 0 1 0 1],[3 2 1 2 1],[4 0 1 0 1]]
import numpy as np
a = [1,2,1,3,1]
b = [2,1,2,1,2]
First Matrix
def get_matrix1(a,b):
d = []
for x in a:
for y in b:
d.append(abs(y-x))
return np.reshape(d,(5,5))
Second Matrix
def get_matrix2():
# Matrix
m1 = get_matrix1(a,b)
print('First Matrix : {}'.format(m1))
# Cumulative Addition
m1[0] = np.cumsum(m1[0])
m1[:,0] = np.cumsum(m1[:,0])
m2 = m1.copy()
print('\nCumulative Addition Matrix : {}'.format(m2))
# Second Matrix
i_rows,j_cols = [0,1,2,3],[0,1,2,3]
edge_rows,edge_cols = [1,2,3,4],[1,2,3,4]
for i,row in zip(i_rows, edge_rows):
for j,col in zip(j_cols, edge_cols):
# old
old = m2[row,col]
print('\nOld : {}'.format(old))
# edges
c,u,l = m2[i,j],m2[i,j+1],m2[i+1,j]
r = (c,u,l)
print('Edges : {}'.format(r))
# new
new = min(r) + old
print('New : {}'.format(new))
# update
m2[row,col] = new
print('Updated Matrix :')
print(m2)
get_matrix2()

Path finding algorithm excercise and working with .txt files

This is a homework which was given to me and I have been struggling with writing the solution.
Write a program that finds the longest adjacent sequence of colors in a matrix(2D grid). Colors are represented by ‘R’, ‘G’, ‘B’ characters (respectively Red, Green and Blue).
You will be provided with 4 individual test cases, which must also be included in your solution.
An example of your solution root directory should look like this:
solutionRootDir
| - (my solution files and folders)
| - tests/
| - test_1
| - test_2
| - test_3
| - test_4
Individual test case input format:
First you should read two whitespace separated 32-bit integers from the provided test case
that represents the size (rows and cols) of the matrix.
Next you should read rows number of newline separated lines of 8-bit characters.
Your program should find and print the longest adjacent sequence (diagonals are not counted as adjacent fields),
and print to the standard output the number.
NOTE: in case of several sequences with the same length – simply print their equal length.
test_1
Provided input:
3 3
R R B
G G R
R B G
Expected Output:
2
test_2
Provided input:
4 4
R R R G
G B R G
R G G G
G G B B
Expected Output:
7
test_3
Provided input:
6 6
R R B B B B
B R B B G B
B G G B R B
B B R B G B
R B R B R B
R B B B G B
Expected Output:
22
test_4
Provided input:
1000 1000
1000 rows of 1000 R’s
Expected Output:
1000000
Your program entry point should accepted from one to four additional parameters.
Those parameters will indicate the names of the test cases that your program should run.
• Example 1: ./myprogram test_1 test_3
• Example 2: ./myprogram test_1 test_2 test_3 test_4
• you can assume that the input from the user will be correct (no validation is required)
import numpy as np
a = int(input("Enter rows: "))
b = int(input("Enter columns: "))
rgb = ["R", "G", "B"]
T = [[0 for col in range(b)] for row in range(a)]
for row in range(a):
for col in range(b):
T[row][col] = np.random.choice(rgb)
for r in T:
for c in r:
print(c, end=" ")
print()
def solution(t):
rows: int = len(t)
cols: int = len(t[0])
longest = np.empty((rows, cols))
longest_sean = 1
for i in range(rows - 1, -1, -1):
for j in range(cols - 1, -1, -1):
target = t[i][j]
current = 1
for ii in range(i, rows):
for jj in range(j, cols):
length = 1
if target == t[ii][jj]:
length += longest[ii][jj]
current = max(current, length)
longest[i][j] = current
longest_sean = max(current, longest_sean)
return longest_sean
print(solution(T))
in order to get the parameters from the console execution you have to use sys.argv so from sys import argv. than convert your text field to python lists like this
def load(file):
with open(file+".txt") as f:
data = f.readlines()
res = []
for row in data:
res.append([])
for element in row:
if element != "\n" and element != " ":
res[-1].append(element)
return res
witch will create a 2 dimentional list of containing "R", "B" and "G". than you can simply look for the longest area of one Value like using this Function:
def findLargest(data):
visited = []
area = []
length = 0
movement = [(1,0), (0,1), (-1,0),(0,-1)]
def recScan(x, y, scanArea):
visited.append((x,y))
scanArea.append((x,y))
for dx, dy in movement:
newX, newY = x+dx, y+dy
if newX >= 0 and newY >= 0 and newX < len(data) and newY < len(data[newX]):
if data[x][y] == data[newX][newY] and (not (newX, newY) in visited):
recScan(newX, newY, scanArea)
return scanArea
for x in range(len(data)):
for y in range(len(data[x])):
if (x, y) not in visited:
newArea = recScan(x, y, [])
if len(newArea) > length:
length = len(newArea)
area = newArea
return length, area
whereby recScan will check all adjacent fields that haven't bean visited jet. than just call the functions like this:
if __name__ == "__main__":
for file in argv[1:]:
data = load(file)
print(findLargest(data))
the argv[1:] is reqired because the first argument passed to python witch is the file you want to execute. my data structure is.
main.py
test_1.txt
test_2.txt
test_3.txt
test_4.txt
and test_1 threw test_4 look like this just with other values.
R R B B B B
B R B B G B
B G G B R B
B B R B G B
R B R B R B
R B B B G B

map array and keep original format

I'm using sparksql dataframes.
df = sql.read.parquet("toy_data")
df.show()
+-----------+----------+
| x| y|
+-----------+----------+
| -4.5707927| -5.282721|
| -5.762503| -4.832158|
| 7.907721| 6.793022|
| 7.4408655| -6.601918|
| -4.2428184| -4.162871|
I have a list of tuples the following structure:
(Row(x=-8.45811653137207, y=-5.179722309112549), ((-1819.748514533043, 47.745243303477764), 333))
where the first ele is a point, the second ele is a (sum_of_points, number_of_points) tuple.
When I divide the sum_of_points by the num_of_points, like this:
new_centers = center_sum_num.map(lambda tup: np.asarray(tup[1][0])/tup[1][1]).collect()
I get the following, which is an array of numpy arrays.
[array([-0.10006594, -6.7719144 ]), array([-0.25844196, 5.28381418]), array([-5.12591623, -4.5685448 ]), array([ 5.40192709, -4.35950824])]
However, I want to keep them points of the original format, like this:
[Row(x=-5.659833908081055, y=7.705344200134277), Row(x=3.17942214012146, y=-9.446121215820312), Row(x=9.128270149230957, y=4.5666022300720215), Row(x=-6.432034969329834, y=-4.432190895080566)]
Meaning I don't want an array of numpy_arrays - I want an array of Row(x = ..., y = ...) thingys.
How can I do this?
My full code is attached for reference:
new_centers = [Row(x=-5.659833908081055, y=7.705344200134277), Row(x=3.17942214012146, y=-9.446121215820312), Row(x=9.128270149230957, y=4.5666022300720215), Row(x=-6.432034969329834, y=-4.432190895080566)]
while old_centers is None or not has_converged(old_centers, new_centers, epsilon) and iteration < max_iterations:
# update centers
old_centers = new_centers
center_pt_1 = points.rdd.map(lambda point: ( old_centers[nearest_center(old_centers, point)[0]], (point, 1) ) )
note that nearest_center()[0] is the index
center_sum_num =center_pt_1.reduceByKey(lambda a, b: ((a[0][0] + b[0][0], a[0][1] + b[0][1]) ,a[1] + b[1]))
new_centers = center_sum_num.map(lambda tup: np.asarray(tup[1][0])/tup[1][1]).collect()
iteration += 1
return new_centers
Define the structure
from pyspark.sql import Row
row = Row("x", "y")
and unpack results:
x = (
Row(x=-8.45811653137207, y=-5.179722309112549),
((-1819.748514533043, 47.745243303477764), 333)
)
f = lambda tup: row(*np.asarray(tup[1][0]) / tup[1][1])
f(x)
## Row(x=-5.4647102538529815, y=0.14337910901945275)

Eliminate for loops in numpy implementation

I have the following dataset in numpy
indices | real data (X) |targets (y)
| |
0 0 | 43.25 665.32 ... |2.4 } 1st block
0 0 | 11.234 |-4.5 }
0 1 ... ... } 2nd block
0 1 }
0 2 } 3rd block
0 2 }
1 0 } 4th block
1 0 }
1 0 }
1 1 ...
1 1
1 2
1 2
2 0
2 0
2 1
2 1
2 1
...
Theses are my variables
idx1 = data[:,0]
idx2 = data[:,1]
X = data[:,2:-1]
y = data[:,-1]
I also have a variable W which is a 3D array.
What I need to do in the code is loop through all the blocks in the dataset and return a scalar number for each block after some computation, then sum up all the scalars, and store it in a variable called cost. Problem is that the looping implementation is very slow, so I'm trying to do it vectorized if possible. This is my current code. Is it possible to do this without for loops in numpy?
IDX1 = 0
IDX2 = 1
# get unique indices
idx1s = np.arange(len(np.unique(data[:,IDX1])))
idx2s = np.arange(len(np.unique(data[:,IDX2])))
# initialize global sum variable to 0
cost = 0
for i1 in idx1s:
for i2 in idx2:
# for each block in the dataset
mask = np.nonzero((data[:,IDX1] == i1) & (data[:,IDX2] == i2))
# get variables for that block
curr_X = X[mask,:]
curr_y = y[mask]
curr_W = W[:,i2,i1]
# calculate a scalar
pred = np.dot(curr_X,curr_W)
sigm = 1.0 / (1.0 + np.exp(-pred))
loss = np.sum((sigm- (0.5)) * curr_y)
# add result to global cost
cost += loss
Here is some sample data
data = np.array([[0,0,5,5,7],
[0,0,5,5,7],
[0,1,5,5,7],
[0,1,5,5,7],
[1,0,5,5,7],
[1,1,5,5,7]])
W = np.zeros((2,2,2))
idx1 = data[:,0]
idx2 = data[:,1]
X = data[:,2:-1]
y = data[:,-1]
That W was tricky... Actually, your blocks are pretty irrelevant, apart from getting the right slice of W to do the np.dot with the corresponding X, so I went the easy route of creating an aligned_W array as follows:
aligned_W = W[:, idx2, idx1]
This is an array of shape (2, rows) where rows is the number of rows of your data set. You can now proceed to do your whole calculation without any for loops as:
from numpy.core.umath_tests import inner1d
pred = inner1d(X, aligned_W.T)
sigm = 1.0 / (1.0 + np.exp(-pred))
loss = (sigm - 0.5) * curr_y
cost = np.sum(loss)
My guess is the major reason your code is slow is the following line:
mask = np.nonzero((data[:,IDX1] == i1) & (data[:,IDX2] == i2))
Because you repeatedly scan your input arrays for small number of rows of interest. So you need to do the following:
ni1 = len(np.unique(data[:,IDX1]))
ni2 = len(np.unique(data[:,IDX2]))
idx1s = np.arange(ni1)
idx2s = np.arange(ni2)
key = data[:,IDX1] * ni2 + data[:,IDX2] # 1D key to the rows
sortids = np.argsort(key) #indices to the sorted key
Then inside the loop instead of
mask=np.nonzero(...)
you need to do
curid = i1 * ni2 + i2
left = np.searchsorted(key, curid, 'left', sorter=sortids)
right=np.searchsorted(key, curid, 'right', sorter=sortids)
mask = sortids[left:right]
I don't think that there is a way to compare numpy array of different sizes without using for loops. Would be hard to decide what is the output meaning and shape of something like
[0,1,2,3,4] == [3,4,2]
The only suggestion that I can give you is to get rid of one of the for loop using itertools.product:
import itertools as it
[...]
idx1s = np.unique(data[:,IDX1])
idx2s = np.unique(data[:,IDX2])
# initialize global sum variable to 0
cost = 0
for i1, i2 in it.product(idx1s, idx2):
# for each block in the dataset
mask = np.nonzero((data[:,IDX1] == i1) & (data[:,IDX2] == i2))
# get variables for that block
curr_X = X[mask,:]
curr_y = y[mask]
[...]
You can also keep mask as a bool array
mask = (data[:,IDX1] == i1) & (data[:,IDX2] == i2)
The output is the same and you have to use anyway the memory to create the bool array. Doing this way saves you some memory and a function evaluation
EDIT
If you know that the indices do not have holes or have few holes, might be worth to remove the part where you define idx1s and idxs2 and change the for loop to
max1, max2 = data[:,[IDX1, IDX2]].max(axis=0)
for i1, i2 in it.product(xrange(max1), xrange(max2)):
[...]
Both xrange and it.product are iterators, so they create only i1 and i2 when you need.
ps: if you are on python3.x use range instead of xrange

Categories