suppose a numpy ndarrary
arr
has shape (100,100,5,5)
The following codes work:
result=np.zeros((arr.shape[0], arr.shape[1], 10))
for i in range(arr.shape[0]):
for j in range(arr.shape[1]):
v=arr[i,j].flatten()
hist, bi= np.histogram(v, bins=10, range=(0,3))
result[i,j] =hist
but it's slow. Is there a more efficient way to write the codes, say avoid the for loops?
Hmm, I thought apply_along_axis would help, but it doesn't seem to make much of a difference, at least at the problem sizes of interest to you. Maybe there's overhead in myhist.
See the code below.
import numpy as np
import time
low = 0.0
high = 3.0
bins = 10
arrshp = (100,100,5,5)
def myhist(xx):
out = np.histogram(xx,bins=bins,range=(low,high))
return out[0]
arr = np.random.uniform(low,high,arrshp)
time1 = time.time()
arr2 = arr.reshape(arrshp[0],arrshp[1],-1)
out_fast = np.apply_along_axis(myhist,-1,arr2)
time2 = time.time()
print('time (secs) fast = ',time2-time1)
time3 = time.time()
out_slow = np.zeros((arr.shape[0],arr.shape[1],bins),dtype='float64')
for i in range(arr.shape[0]):
for j in range(arr.shape[1]):
v = arr[i,j].flatten()
_hh = np.histogram(v, bins=bins, range=(low,high))
out_slow[i,j,:] = _hh[0]
time4 = time.time()
print('norm diff = ',np.linalg.norm(out_fast-out_slow))
print('time (secs) slow = ',time4-time3)
Related
I need to build a relief profile graph by coordinates, I have a csv file with 12,000,000 lines. searching through a csv file of the same height takes about 2 - 2.5 seconds. I rewrote the csv to parquet and it helped me save some time, it takes about 1.7 - 1 second to find one height. However, I need to build a profile for 500 - 2000 values, which makes the time very long. In the future, you may have to increase the base of the csv file, which will slow down this process even more. In this regard, my question is, is it possible to somehow reduce the processing time of values?
Code example:
import dask.dataframe as dk
import numpy as np
import pandas as pd
import time
filename = 'n46_e032_1arc_v3.csv'
df = dk.read_csv(filename)
df.to_parquet('n46_e032_1arc_v3_parquet')
Latitude1y, Longitude1x = 46.6276, 32.5942
Latitude2y, Longitude2x = 46.6451, 32.6781
sec, steps, k = 0.00027778, 1, 11.73
Latitude, Longitude = [Latitude1y], [Longitude1x]
sin, cos = Latitude2y - Latitude1y, Longitude2x - Longitude1x
y, x = Latitude1y, Longitude1x
while Latitude[-1] < Latitude2y and Longitude[-1] < Longitude2x:
y, x, steps = y + sec * k * sin, x + sec * k * cos, steps + 1
Latitude.append(y)
Longitude.append(x)
time_start = time.time()
long, elevation_data = [], []
df2 = dk.read_parquet('n46_e032_1arc_v3_parquet')
for i in range(steps + 1):
elevation_line = df2[(Longitude[i] <= df2['x']) & (df2['x'] <= Longitude[i] + sec) &
(Latitude[i] <= df2['y']) & (df2['y'] <= Latitude[i] + sec)].compute()
elevation = np.asarray(elevation_line.z.tolist())
if elevation[-1] < 0:
elevation_data.append(0)
else:
elevation_data.append(elevation[-1])
long.append(30 * i)
plt.bar(long, elevation_data, width = 30)
plt.show()
print(time.time() - time_start)
Here's one way to solve this problem using KD trees. A KD tree is a data structure for doing fast nearest-neighbor searches.
import scipy.spatial
tree = scipy.spatial.KDTree(df[['x', 'y']].values)
elevations = df['z'].values
long, elevation_data = [], []
for i in range(steps):
lon, lat = Longitude[i], Latitude[i]
dist, idx = tree.query([lon, lat])
elevation = elevations[idx]
if elevation < 0:
elevation = 0
elevation_data.append(elevation)
long.append(30 * i)
Note: if you can make assumptions about the data, like "all of the points in the CSV are equally spaced," faster algorithms are possible.
It looks like your data might be on a regular grid. If (and only if) every combination of x and y exist in your data, then it probably makes sense to turn this into a labeled 2D array of points, after which querying the correct position will be very fast.
For this, I'll use xarray, which is essentially pandas for N-dimensional data, and integrates well with dask:
# bring the dataframe into memory
df = dk.read('n46_e032_1arc_v3_parquet').compute()
da = df.set_index(["y", "x"]).z.to_xarray()
# now you can query the nearest points:
desired_lats = xr.DataArray([46.6276, 46.6451], dims=["point"])
desired_lons = xr.DataArray([32.5942, 32.6781], dims=["point"])
subset = da.sel(y=desired_lats, x=desired_lons, method="nearest")
# if you'd like, you can return to pandas:
subset_s = subset.to_series()
# you could do this only once, and save the reshaped array as a zarr store:
ds = da.to_dataset(name="elevation")
ds.to_zarr("n46_e032_1arc_v3.zarr")
Is it possible without using parallelization (Swifter, Parallel) to make an instant calculation immediately without passing through the index, for example through the use of the "apply"-function for all dataset?
%%time
import random
df = pd.DataFrame({'A':random.sample(range(200), 200)})
for j in range(200):
for i in df.index:
df.loc[i,'A_last_{}'.format(j)] = df.loc[(df.index < i) & (df.index >= i - j),'A'].mean()
%%time
import random
df = pd.DataFrame({'A':random.sample(range(200), 200)})
First calculate the sums.
df[1] = df['A'].shift()
for j in range(2, 200):
df[j] = df[j-1].fillna(0) + df['A'].shift(j)
Then do the division for means and take care of the formatting
df = df.set_index('A')
df.divide(df.columns, axis=1)\
.fillna(method='ffill', axis=1)\
.rename(lambda x: f'A_last_{x}', axis=1)\
.reset_index()
How do you optimize this code?
At the moment it is running to slow for the amount of data that goes through this loop. This code runs 1-nearest neighbor. It will predict the label of the training_element based off the p_data_set
# [x] , [[x1],[x2],[x3]], [l1, l2, l3]
def prediction(training_element, p_data_set, p_label_set):
temp = np.array([], dtype=float)
for p in p_data_set:
temp = np.append(temp, distance.euclidean(training_element, p))
minIndex = np.argmin(temp)
return p_label_set[minIndex]
Use a k-D tree for fast nearest-neighbour lookups, e.g. scipy.spatial.cKDTree:
from scipy.spatial import cKDTree
# I assume that p_data_set is (nsamples, ndims)
tree = cKDTree(p_data_set)
# training_elements is also assumed to be (nsamples, ndims)
dist, idx = tree.query(training_elements, k=1)
predicted_labels = p_label_set[idx]
You could use distance.cdist to directly get the distances temp and then use .argmin() to get min-index, like so -
minIndex = distance.cdist(training_element[None],p_data_set).argmin()
Here's an alternative approach using np.einsum -
subs = p_data_set - training_element
minIndex = np.einsum('ij,ij->i',subs,subs).argmin()
Runtime test
Well I was thinking cKDTree would easily beat cdist, but I guess training_element being a 1D array isn't too heavy for cdist and I am seeing it to beat out cKDTree instead by a good 10x+ margin!
Here's the timing results -
In [422]: # Setup arrays
...: p_data_set = np.random.randint(0,9,(40000,100))
...: training_element = np.random.randint(0,9,(100,))
...:
In [423]: def tree_based(p_data_set,training_element): ##ali_m's soln
...: tree = cKDTree(p_data_set)
...: dist, idx = tree.query(training_element, k=1)
...: return idx
...:
...: def einsum_based(p_data_set,training_element):
...: subs = p_data_set - training_element
...: return np.einsum('ij,ij->i',subs,subs).argmin()
...:
In [424]: %timeit tree_based(p_data_set,training_element)
1 loops, best of 3: 210 ms per loop
In [425]: %timeit einsum_based(p_data_set,training_element)
100 loops, best of 3: 17.3 ms per loop
In [426]: %timeit distance.cdist(training_element[None],p_data_set).argmin()
100 loops, best of 3: 14.8 ms per loop
Python can be quite fast programming language if used properly.
This is my suggestion (faster_prediction):
import numpy as np
import time
def euclidean(a,b):
return np.linalg.norm(a-b)
def prediction(training_element, p_data_set, p_label_set):
temp = np.array([], dtype=float)
for p in p_data_set:
temp = np.append(temp, euclidean(training_element, p))
minIndex = np.argmin(temp)
return p_label_set[minIndex]
def faster_prediction(training_element, p_data_set, p_label_set):
temp = np.tile(training_element, (p_data_set.shape[0],1))
temp = np.sqrt(np.sum( (temp - p_data_set)**2 , 1))
minIndex = np.argmin(temp)
return p_label_set[minIndex]
training_element = [1,2,3]
p_data_set = np.random.rand(100000, 3)*10
p_label_set = np.r_[0:p_data_set.shape[0]]
t1 = time.time()
result_1 = prediction(training_element, p_data_set, p_label_set)
t2 = time.time()
t3 = time.time()
result_2 = faster_prediction(training_element, p_data_set, p_label_set)
t4 = time.time()
print "Execution time 1:", t2-t1, "value: ", result_1
print "Execution time 2:", t4-t3, "value: ", result_2
print "Speed up: ", (t4-t3) / (t2-t1)
I get the following result on pretty old laptop:
Execution time 1: 21.6033108234 value: 9819
Execution time 2: 0.0176379680634 value: 9819
Speed up: 1224.81857013
which makes me think I must have done some stupid mistake :)
In case of very huge data, where memory might be an issue, I suggest using Cython or implementing function in C++ and wrapping it in python.
I am building machine learning models for a certain data set. Then, based on the constraints and bounds for the outputs and inputs, I am trying to find the input parameters for the most minimized answer.
The problem which I am facing is that, when the model is a linear regression model or something like lasso, the minimization works perfectly fine.
However, when the model is "Decision Tree", it constantly returns the very initial value that is given to it. So basically, it does not enforce the constraints.
import numpy as np
import pandas as pd
from scipy.optimize import minimize
I am using the very first sample from the input data set for the optimization. As it is only one sample, I need to reshape it to (1,-1) as well.
x = df_in.iloc[0,:]
x = np.array(x)
x = x.reshape(1,-1)
This is my Objective function:
def objective(x):
x = np.array(x)
x = x.reshape(1,-1)
y = 0
for n in range(df_out.shape[1]):
y = Model[n].predict(x)
Y = y[0]
return Y
Here I am defining the bounds of inputs:
range_max = pd.DataFrame(range_max)
range_min = pd.DataFrame(range_min)
B_max=[]
B_min =[]
for i in range(range_max.shape[0]):
b_max = range_max.iloc[i]
b_min = range_min.iloc[i]
B_max.append(b_max)
B_min.append(b_min)
B_max = pd.DataFrame(B_max)
B_min = pd.DataFrame(B_min)
bnds = pd.concat([B_min, B_max], axis=1)
These are my constraints:
con_min = pd.DataFrame(c_min)
con_max = pd.DataFrame(c_max)
Here I am defining the constraint function:
def const(x):
x = np.array(x)
x = x.reshape(1,-1)
Y = []
for n in range(df_out.shape[1]):
y = Model[n].predict(x)[0]
Y.append(y)
Y = pd.DataFrame(Y)
a4 =[]
for k in range(Y.shape[0]):
a1 = Y.iloc[k,0] - con_min.iloc[k,0]
a2 = con_max.iloc[k, 0] - Y.iloc[k,0]
a3 = [a2,a1]
a4 = np.concatenate([a4, a3])
return a4
c = const(x)
con = {'type': 'ineq', 'fun': const}
This is where I try to minimize. I do not pick a method as the automatically picked model has worked so far.
sol = minimize(fun = objective, x0=x,constraints=con, bounds=bnds)
So the actual constraints are:
c_min = [0.20,1000]
c_max = [0.3,1600]
and the max and min range for the boundaries are:
range_max = [285,200,8,85,0.04,1.6,10,3.5,20,-5]
range_min = [215,170,-1,60,0,1,6,2.5,16,-18]
I think you should check the output of 'sol'. At times, the algorithm is not able to perform line search completely. To check for this, you should check message associated with 'sol'. In such a case, the optimizer returns initial parameters itself. There may be various reasons of this behavior. In a nutshell, please check the output of sol and act accordingly.
Arad,
If you have not yet resolved your issue, try using scipy.optimize.differential_evolution instead of scipy.optimize.minimize. I ran into similar issues, particularly with decision trees because of their step-like behavior resulting in infinite gradients.
I am trying to implement a time fold function to be 'map'ed to various partitions of a dask dataframe which in turn changes the shape of the dataframe in question (or alternatively produces a new dataframe with the altered shape). This is how far I have gotten. The result 'res' returned on compute is a list of 3 delayed objects. When I try to compute each of them in a loop (last tow lines of code) this results in a "TypeError: 'DataFrame' object is not callable" After going through the examples for map_partitions, I also tried altering the input DF (inplace) in the function with no return value which causes a similar TypeError with NoneType. What am I missing?
Also, looking at the visualization (attached) I feel like there is a need for reducing the individually computed (folded) partitions into a single DF. How do I do this?
#! /usr/bin/env python
# Start dask scheduler and workers
# dask-scheduler &
# dask-worker --nthreads 1 --nprocs 6 --memory-limit 3GB localhost:8786 --local-directory /dev/shm &
from dask.distributed import Client
from dask.delayed import delayed
import pandas as pd
import numpy as np
import dask.dataframe as dd
import math
foldbucketsecs=30
periodicitysecs=15
secsinday=24 * 60 * 60
chunksizesecs=60 # 1 minute
numts = 5
start = 1525132800 # 01/05
end = 1525132800 + (3 * 60) # 3 minute
c = Client('127.0.0.1:8786')
def fold(df, start, bucket):
return df
def reduce_folds(df):
return df
def load(epoch):
idx = []
for ts in range(0, chunksizesecs, periodicitysecs):
idx.append(epoch + ts)
d = np.random.rand(chunksizesecs/periodicitysecs, numts)
ts = []
for i in range(0, numts):
tsname = "ts_%s" % (i)
ts.append(tsname)
gts.append(tsname)
res = pd.DataFrame(index=idx, data=d, columns=ts, dtype=np.float64)
res.index = pd.to_datetime(arg=res.index, unit='s')
return res
gts = []
load(start)
cols = len(gts)
idx1 = pd.DatetimeIndex(start=start, freq=('%sS' % periodicitysecs), end=start+periodicitysecs, dtype='datetime64[s]')
meta = pd.DataFrame(index=idx1[:0], data=[], columns=gts, dtype=np.float64)
dfs = [delayed(load)(fn) for fn in range(start, end, chunksizesecs)]
from_delayed = dd.from_delayed(dfs, meta, 'sorted')
nfolds = int(math.ceil((end - start)/foldbucketsecs))
cprime = nfolds * cols
gtsnew = []
for i in range(0, cprime):
gtsnew.append("ts_%s,fold=%s" % (i%cols, i/cols))
idx2 = pd.DatetimeIndex(start=start, freq=('%sS' % periodicitysecs), end=start+foldbucketsecs, dtype='datetime64[s]')
meta = pd.DataFrame(index=idx2[:0], data=[], columns=gtsnew, dtype=np.float64)
folded_df = from_delayed.map_partitions(delayed(fold)(from_delayed, start, foldbucketsecs), meta=meta)
result = c.submit(reduce_folds, folded_df)
c.gather(result).visualize(filename='/usr/share/nginx/html/svg/df4.svg')
res = c.gather(result).compute()
for f in res:
f.compute()
Never mind! It was my fault, instead of wrapping my function in delayed I simply passed it to the map_partitions call like so and it worked.
folded_df = from_delayed.map_partitions(fold, start, foldbucketsecs, nfolds, meta=meta)