In my code, I am trying to extract data from csv file to use in the function, but it doesnt output anything, and gives no error. My code works because I tried it with just numpy array as inputs. not sure why it doesnt work with panda.
import numpy as np
import pandas as pd
import os
# change the current directory to the directory where the running script file is
os.chdir(os.path.dirname(os.path.abspath(__file__)))
# finding best fit line for y=mx+b by iteration
def gradient_descent(x,y):
m_iter = b_iter = 1 #starting point
iteration = 10000
n = len(x)
learning_rate = 0.05
last_mse = 10000
#take baby steps to reach global minima
for i in range(iteration):
y_predicted = m_iter*x + b_iter
#mse = 1/n*sum([value**2 for value in (y-y_predicted)]) # cost function to minimize
mse = 1/n*sum((y-y_predicted)**2) # cost function to minimize
if (last_mse - mse)/mse < 0.001:
break
# recall MSE formula is 1/n*sum((yi-y_predicted)^2), where y_predicted = m*x+b
# using partial deriv of MSE formula, d/dm and d/db
dm = -(2/n)*sum(x*(y-y_predicted))
db = -(2/n)*sum((y-y_predicted))
# use current predicted value to get the next value for prediction
# by using learning rate
m_iter = m_iter - learning_rate*dm
b_iter = b_iter - learning_rate*db
print('m is {}, b is {}, cost is {}, iteration {}'.format(m_iter,b_iter,mse,i))
last_mse = mse
#x = np.array([1,2,3,4,5])
#y = np.array([5,7,8,10,13])
#gradient_descent(x,y)
df = pd.read_csv('Linear_Data.csv')
x = df['Area']
y = df['Price']
gradient_descent(x,y)
My code works because I tried it with just numpy array as inputs. not sure why it doesnt work with panda.
Well no, your code also works with pandas dataframes:
df = pd.DataFrame({'Area': [1,2,3,4,5], 'Price': [5,7,8,10,13]})
x = df['Area']
y = df['Price']
gradient_descent(x,y)
Above will give you the same output as with numpy arrays.
Try to check what's in Linear_Data.csv and/or add some print statements in the gradient_descent function just to check your assumptions. I would suggest to first of all add a print statement before the condition with the break statement:
print(last_mse, mse)
if (last_mse - mse)/mse < 0.001:
break
Related
It might not even be possible, but I would like to express the following code without the for-loop.
tf.scan is prohibitively slow and therefore not a good solution.
I am perfectly happy to accept any answer which gives a solution or an argument why this is not possible.
import tensorflow as tf
import matplotlib.pyplot as plt
# Some data
random_series = tf.reshape(tf.math.cumsum(tf.random.normal([100])),[1,-1])
# a mesh_grid of "co-distance"
random_mesh_gain = 1 - tf.matmul(random_series,tf.math.reciprocal(random_series), True, False)
# lower triangular matrix
random_tri = tf.linalg.band_part(random_mesh_gain, 0, -1)
# some lambda working on a series-type data
drop = 0.5
lambda_map = lambda series: tf.math.floor(series/interval)*interval - drop
# apply map
random_img = tf.map_fn(lambda_map, random_tri)
# init preceding and output list sl_full
preceding = - drop * tf.ones(tf.transpose(random_img).shape[0],dtype=tf.float32)
sl_full = []
for a in tf.transpose(random_img):
prec_a_max = tf.reduce_max(tf.stack([preceding, a]),axis=0)
preceding = prec_a_max
sl_full.append(prec_a_max)
# create tensor from list
sl_full = tf.transpose(tf.stack(sl_full))
plt.imshow(sl_full,origin="lower")
i'm trying to solve tsp with OR-tools for a problem of something like 80,000 nodes, the problem is, I need a huge distance matrix that takes to much memory ,so its infeasible and i don't get a solution.
so:
is there an option to work with partial distance matrix in or-tools?
if not is there a way to improve my code?
is there another external solver that can work for this task in python?
import math
from collections import namedtuple
import random
import time
from collections import namedtuple
from sklearn.metrics.pairwise import euclidean_distances
import numpy as np
import numba
from scipy.spatial import distance_matrix
from sklearn.metrics.pairwise import euclidean_distances
from math import sqrt
Point = namedtuple("Point", ['x', 'y'])
def solve_it(input_data):
# Modify this code to run your optimization algorithm
global POINTS
# parse the input
lines = input_data.split('\n')
nodeCount = int(lines[0])
points = []
for i in range(1, nodeCount+1):
line = lines[i]
parts = line.split()
points.append(Point(float(parts[0]), float(parts[1])))
#2.routing with or tools
def dist_matrix(nodeCount,points):
data=[]
for k in range(len(points)):
data.append([int(points[k].x),int(points[k].y)])
D=euclidean_distances(data, data)
return D
def create_data_model(D):
"""Stores the data for the problem."""
data = {}
data['distance_matrix'] = D # yapf: disable
data['num_vehicles'] = 1
data['depot'] = 0
return data
def print_solution(manager, routing, solution):
index = routing.Start(0)
plan_output = []#Route for vehicle 0:\n'
route_distance = 0
while not routing.IsEnd(index):
plan_output.append(manager.IndexToNode(index))
index = solution.Value(routing.NextVar(index))
return plan_output
def or_main(nodeCount,points):
from ortools.constraint_solver import routing_enums_pb2
from ortools.constraint_solver import pywrapcp
"""Entry point of the program."""
# Instantiate the data problem.
global sol
D=dist_matrix(nodeCount,points)
data = create_data_model(D)
# Create the routing index manager.
manager = pywrapcp.RoutingIndexManager(len(data['distance_matrix']),
data['num_vehicles'], data['depot'])
# Create Routing Model.
routing = pywrapcp.RoutingModel(manager)
def distance_callback(from_index, to_index):
"""Returns the distance between the two nodes."""
# Convert from routing variable Index to distance matrix NodeIndex.
from_node = manager.IndexToNode(from_index)
to_node = manager.IndexToNode(to_index)
return data['distance_matrix'][from_node][to_node]
transit_callback_index = routing.RegisterTransitCallback(distance_callback)
# Define cost of each arc.
routing.SetArcCostEvaluatorOfAllVehicles(transit_callback_index)
# Setting first solution heuristic.
search_parameters = pywrapcp.DefaultRoutingSearchParameters()
search_parameters.local_search_metaheuristic = (
routing_enums_pb2.LocalSearchMetaheuristic.GUIDED_LOCAL_SEARCH)
k = 100
if nodeCount <= 100:
k = 30
elif 100 <= nodeCount <= 1000:
k = 300
elif nodeCount > 1000:
k = 17000
search_parameters.time_limit.seconds =k
search_parameters.log_search = True
# Solve the problem.
solution = routing.SolveWithParameters(search_parameters)
# #print solution on console.
if solution:
sol=print_solution(manager, routing, solution)
return sol
######################################################################
solution=or_main(nodeCount,points)
# calculate the length of the tour
obj = length(points[solution[-1]], points[solution[0]])
for index in range(0, nodeCount-1):
obj += length(points[solution[index]], points[solution[index+1]])
# prepare the solution in the specified output format
output_data = '%.2f' % obj + ' ' + str(0) + '\n'
output_data += ' '.join(map(str, solution))
return output_data
if __name__ == '__main__':
import sys
if len(sys.argv) > 1:
file_location = sys.argv[1].strip()
with open(file_location, 'r') as input_data_file:
input_data = input_data_file.read()
#print(solve_it(input_data))
else:
print('This test requires an input file. Please select one from the data directory. (i.e. python solver.py ./data/tsp_51_1)')
Suppose that I have an array
a = np.array([[1,2.5,3,4],[1, 2.5, 3,3]])
I want to find the mode of each column without using stats.mode().
The only way I can think of is the following:
result = np.zeros(a.shape[1])
for i in range(len(result)):
curr_col = a[:,i]
result[i] = curr_col[np.argmax(np.unique(curr_col, return_counts = True))]
update:
There is some error in the above code and the correct one should be:
values, counts = np.unique(a[:,i], return_counts = True)
result[i] = values[np.argmax(counts)]
I have to use the loop because np.unique does not output compatible result for each column and there is no way to use np.bincount because the dtype is not int.
If you look at the numpy.unique documentation, this function returns the values and the associated counts (because you specified return_counts=True). A slight modification of your code is necessary to give the correct result. What you are trying todo is to find the value associated to the highest count:
import numpy as np
a = np.array([[1,5,3,4],[1,5,3,3],[1,5,3,3]])
result = np.zeros(a.shape[1])
for i in range(len(result)):
values, counts = np.unique(a[:,i], return_counts = True)
result[i] = values[np.argmax(counts)]
print(result)
Output:
% python3 script.py
[1. 5. 3. 4.]
Here is a code tha compares your solution with the scipy.stats.mode function:
import numpy as np
import scipy.stats as sps
import time
a = np.random.randint(1,100,(100,100))
t_start = time.time()
result = np.zeros(a.shape[1])
for i in range(len(result)):
values, counts = np.unique(a[:,i], return_counts = True)
result[i] = values[np.argmax(counts)]
print('Timer 1: ', (time.time()-t_start), 's')
t_start = time.time()
result_2 = sps.mode(a, axis=0).mode
print('Timer 2: ', (time.time()-t_start), 's')
print('Matrices are equal!' if np.allclose(result, result_2) else 'Matrices differ!')
Output:
% python3 script.py
Timer 1: 0.002721071243286133 s
Timer 2: 0.003339052200317383 s
Matrices are equal!
I tried several values for parameters and your code is actually faster than scipy.stats.mode function so it is probably close to optimal.
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)