MATEMATICAS APLICADAS, VECTORES CLASE INICIAL

python numpy/scipy curve fitting

librerias importantes

import pandas_datareader as pdr

import datetime

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

 scipy.optimize.curve_fit tries to fit a function f that you must know to a set of points.

This is a simple 3 degree polynomial fit using numpy.polyfit and poly1d, the first performs a least squares polynomial fit and the second calculates the new points:

import numpy as np
import matplotlib.pyplot as plt

points = np.array([(1, 1), (2, 4), (3, 1), (9, 3)])
# get x and y vectors
x = points[:,0]
y = points[:,1]

# calculate polynomial
z = np.polyfit(x, y, 3)
f = np.poly1d(z)

# calculate new x's and y's
x_new = np.linspace(x[0], x[-1], 50)
y_new = f(x_new)

plt.plot(x,y,'o', x_new, y_new)
plt.xlim([x[0]-1, x[-1] + 1 ])
plt.show()

share  improve this answer   

 import numpy as np

import matplotlib.pyplot as plt

points = np.array([

(197,3116.2),

(198,3103.0),

(199,3156.1),

(200,3078.1),

(201,3008.7),

(202,2954.9),

(203,2960.5),

(204,3129.0),

(205,2999.9),

(206,3019.8),

(207,3095.1),

(208,3174.1),

(209,3144.9),

(210,3148.7),

(211,3221.3),

(212,3125.0),

(213,3199.2),

(214,3100.0),

(215,3195.7),

(216,3190.6),

(217,3286.6),

(218,3442.9),

(219,3443.6),

(220,3363.7),

(221,3338.6),

(222,3272.7),

(223,3207.2),

(224,3217.0),

(225,3184.9),

(226,3176.4),

(227,3204.4),

(228,3207.0),

(229,3286.3),

(230,3162.8),

(231,3211.0),

(232,3036.1),

(233,3004.5),

(234,3048.4),

(235,3241.2),

(236,3322.0),

(237,3311.4),

(238,3143.7),

(239,3035.0),

(240,3137.4),

(241,3110.3),

(242,3128.8),

(243,3131.1),

(244,3135.7),

(245,3105.5),

(246,3117.0),

(247,3099.4),

(248,3098.4),

(249,3118.1),

(250,3185.1),

(251,3195.3),

(252,3168.0),

(253,3220.1),

(254,3203.5),

(255,3186.7),

(256,3162.6),

(257,3158.0),

(258,3177.3),

(259,3104.2),

(260,3101.5),

(261,3116.4),

(262,3157.0),

(263,3165.1),

(264,3241.0),

(265,3236.1),

(266,3201.6),

(267,3206.2),

(268,3206.5),

(269,3185.3),

(270,3172.7),

(271,3284.0),

(272,3322.0),

(273,3285.9),

(274,3256.9),

(275,3186.6),

(276,3218.5)])

# get x and y vectors

x = points[:,0]

y = points[:,1]

# calculate polynomial

z = np.polyfit(x, y, 3)

f = np.poly1d(z)

# calculate new x's and y's

x_new = np.linspace(x[0], x[-1], 50)

y_new = f(x_new)

plt.plot(x,y,'o', x_new, y_new)

plt.xlim([x[0]-1, x[-1] + 1 ])

plt.show()

*********************************************

C:\pythonPRACTICA>python fit2.py

z=

[ 0.08703704 -0.81349206  1.69312169 -0.03968254]

np.poly1d(z)=

         3          2

0.08704 x - 0.8135 x + 1.693 x - 0.03968

p(0.5) =

0.6143849206349206

p(3.5)) =

-0.34732142857142845

p(10) =

22.579365079364862

p30 = np.poly1d(np.polyfit(x, y, 30)) =

           30             29             28             27

-7.16e-22 x  - 3.532e-21 x  - 1.736e-20 x  - 8.496e-20 x

              26             25             24             23

 - 4.132e-19 x  - 1.994e-18 x  - 9.516e-18 x  - 4.476e-17 x

              22             21             20             19

 - 2.063e-16 x  - 9.223e-16 x  - 3.934e-15 x  - 1.548e-14 x

             18             17             16             15

 - 5.15e-14 x  - 9.843e-14 x  + 4.796e-13 x  + 8.283e-12 x

              14             13             12             11

 + 7.662e-11 x  + 5.899e-10 x  + 4.133e-09 x  + 2.714e-08 x

              10             9             8             7

 + 1.687e-07 x  + 9.879e-07 x + 5.346e-06 x + 2.539e-05 x

              6             5           4           3          2

 + 8.972e-05 x + 2.249e-05 x - 0.00352 x - 0.03957 x - 0.2124 x + 1.055 x - 1.405e-15

p30(4) =

-0.7999999999999977

p30(5) =

-0.9999999999999879

p30(4.5) =

-0.11804856672740378

+++++++++++++++++++++++++++++++++++

OUT

INPUT

import numpy as np

import matplotlib.pyplot as plt

import warnings

x = np.array([0.0, 1.0, 2.0, 3.0,  4.0,  5.0])

y = np.array([0.0, 0.8, 0.9, 0.1, -0.8, -1.0])

z = np.polyfit(x, y, 3)

print("z=")

print(z)

p = np.poly1d(z)

print("np.poly1d(z)=")

print(p)

print("p(0.5) =")

print(p(0.5))

print("p(3.5)) =")

print(p(3.5))

print("p(10) =")

print(p(10))

warnings.simplefilter('ignore', np.RankWarning)

p30 = np.poly1d(np.polyfit(x, y, 30))

print("p30 = np.poly1d(np.polyfit(x, y, 30)) =")

print(p30)

print("p30(4) =")

print(p30(4))

print("p30(5) =")

print(p30(5))

print("p30(4.5) =")

print(p30(4.5))

xp = np.linspace(-2, 6, 100)

_ = plt.plot(x, y, '.', xp, p(xp), '-', xp, p30(xp), '--')

plt.ylim(-2,2)

plt.show()

exactamente el mismo resultado, mas convieniente para usar csv

import numpy as np

import matplotlib.pyplot as plt

import warnings

points = np.array([(0.0, 0.0), (1.0, 0.8), (2.0, 0.9), (3.0, 0.1),(4.0, -0.8),(5.0, -1.0)])

# get x and y vectors

x = points[:,0]

y = points[:,1]

# calculate polynomial

#z = np.polyfit(x, y, 3)

#f = np.poly1d(z)

###########

#x = np.array([0.0, 1.0, 2.0, 3.0,  4.0,  5.0])

#y = np.array([0.0, 0.8, 0.9, 0.1, -0.8, -1.0])

z = np.polyfit(x, y, 3)

print("z=")

print(z)

p = np.poly1d(z)

print("np.poly1d(z)=")

print(p)

print("p(0.5) =")

print(p(0.5))

print("p(3.5)) =")

print(p(3.5))

print("p(10) =")

print(p(10))

warnings.simplefilter('ignore', np.RankWarning)

p30 = np.poly1d(np.polyfit(x, y, 30))

print("p30 = np.poly1d(np.polyfit(x, y, 30)) =")

print(p30)

print("p30(4) =")

print(p30(4))

print("p30(5) =")

print(p30(5))

print("p30(4.5) =")

print(p30(4.5))

xp = np.linspace(-2, 6, 100)

_ = plt.plot(x, y, '.', xp, p(xp), '-', xp, p30(xp), '--')

plt.ylim(-2,2)

plt.show()

great AMZN, 

out

import numpy as np

import matplotlib.pyplot as plt

import warnings

points = np.array([

(197,3116.2),

(198,3103.0),

(199,3156.1),

(200,3078.1),

(201,3008.7),

(202,2954.9),

(203,2960.5),

(204,3129.0),

(205,2999.9),

(206,3019.8),

(207,3095.1),

(208,3174.1),

(209,3144.9),

(210,3148.7),

(211,3221.3),

(212,3125.0),

(213,3199.2),

(214,3100.0),

(215,3195.7),

(216,3190.6),

(217,3286.6),

(218,3442.9),

(219,3443.6),

(220,3363.7),

(221,3338.6),

(222,3272.7),

(223,3207.2),

(224,3217.0),

(225,3184.9),

(226,3176.4),

(227,3204.4),

(228,3207.0),

(229,3286.3),

(230,3162.8),

(231,3211.0),

(232,3036.1),

(233,3004.5),

(234,3048.4),

(235,3241.2),

(236,3322.0),

(237,3311.4),

(238,3143.7),

(239,3035.0),

(240,3137.4),

(241,3110.3),

(242,3128.8),

(243,3131.1),

(244,3135.7),

(245,3105.5),

(246,3117.0),

(247,3099.4),

(248,3098.4),

(249,3118.1),

(250,3185.1),

(251,3195.3),

(252,3168.0),

(253,3220.1),

(254,3203.5),

(255,3186.7),

(256,3162.6),

(257,3158.0),

(258,3177.3),

(259,3104.2),

(260,3101.5),

(261,3116.4),

(262,3157.0),

(263,3165.1),

(264,3241.0),

(265,3236.1),

(266,3201.6),

(267,3206.2),

(268,3206.5),

(269,3185.3),

(270,3172.7),

(271,3284.0),

(272,3322.0),

(273,3285.9),

(274,3256.9),

(275,3186.6),

(276,3218.5)])

# get x and y vectors

x = points[:,0]

y = points[:,1]

# calculate polynomial

#z = np.polyfit(x, y, 3)

#f = np.poly1d(z)

###########

#x = np.array([0.0, 1.0, 2.0, 3.0,  4.0,  5.0])

#y = np.array([0.0, 0.8, 0.9, 0.1, -0.8, -1.0])

z = np.polyfit(x, y, 3)

print("z=")

print(z)

p = np.poly1d(z)

print("np.poly1d(z)=")

print(p)

print("p(0.5) =")

print(p(0.5))

print("p(3.5)) =")

print(p(3.5))

print("p(10) =")

print(p(10))

warnings.simplefilter('ignore', np.RankWarning)

p30 = np.poly1d(np.polyfit(x, y, 30))

print("p30 = np.poly1d(np.polyfit(x, y, 30)) =")

print(p30)

print("p30(4) =")

print(p30(4))

print("p30(5) =")

print(p30(5))

print("p30(4.5) =")

print(p30(4.5))

#xp = np.linspace(-2, 6, 100)

xp = np.linspace(x[0], x[-1], 50)

_ = plt.plot(x, y, '.', xp, p(xp), '-', xp, p30(xp), '--')

#plt.ylim(-2,2)

plt.xlim([x[0]-1, x[-1] + 1 ])

plt.show()

*******************************

great , aproximacion 5 

rows 197 a 276

z=

[ 4.48573513e-03 -3.20336361e+00  7.59164990e+02 -5.65254060e+04]

np.poly1d(z)=

          3         2

0.004486 x - 3.203 x + 759.2 x - 5.653e+04

p(0.5) =

-56146.62379395407

p(3.5)) =

-53907.377422800346

p(10) =

-49249.60673658942

p30 = np.poly1d(np.polyfit(x, y, 30)) =

           30             29             28             27

-1.59e-61 x  + 1.569e-58 x  - 3.283e-56 x  - 7.982e-54 x

              26             25            24             23

 + 9.918e-52 x  + 6.817e-49 x  + 9.43e-47 x  - 2.052e-44 x

             22             21             20             19

 - 1.23e-41 x  - 2.307e-39 x  + 1.338e-37 x  + 2.061e-34 x

              18             17             16             15

 + 5.818e-32 x  + 4.532e-30 x  - 2.683e-27 x  - 1.219e-24 x

              14             13             12            11

 - 2.067e-22 x  + 2.177e-20 x  + 2.204e-17 x  + 5.23e-15 x

              10             9             8             7            6

 - 5.978e-14 x  - 4.019e-10 x - 1.023e-07 x + 4.885e-06 x + 0.008613 x

          5         4             3             2

 + 1.133 x - 508.1 x - 1.088e+05 x + 4.835e+07 x - 5.629e+09 x + 2.237e+11

p30(4) =

201965505129.64587

p30(5) =

196765049008.72754

p30(4.5) =

199353571921.81915

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

import numpy as np

import matplotlib.pyplot as plt

import warnings

points = np.array([(1,1781.6),

(2,1770.0),

(3,1760.7),

(4,1740.5),

(5,1751.6),

(6,1749.5),

(7,1739.2),

(8,1748.7),

(9,1760.3),

(10,1760.9),

(11,1769.2),

(12,1790.7),

(13,1784.0),

(14,1792.3),

(15,1786.5),

(16,1793.0),

(17,1789.2),

(18,1868.8),

(19,1869.8),

(20,1846.9),

(21,1847.8),

(22,1898.0),

(23,1875.0),

(24,1902.9),

(25,1906.9),

(26,1892.0),

(27,1901.1),

(28,1883.2),

(29,1891.3),

(30,1869.4),

(31,1862.0),

(32,1877.9),

(33,1864.7),

(34,1892.0),

(35,1887.5),

(36,1884.6),

(37,1861.6),

(38,1828.3),

(39,1853.3),

(40,1858.0),

(41,1870.7),

(42,2008.7),

(43,2004.2),

(44,2049.7),

(45,2039.9),

(46,2050.2),

(47,2079.3),

(48,2133.9),

(49,2150.8),

(50,2160.0),

(51,2149.9),

(52,2134.9),

(53,2155.7),

(54,2170.2),

(55,2153.1),

(56,2096.0),

(57,2009.3),

(58,1972.7),

(59,1979.6),

(60,1884.3),

(61,1883.8),

(62,1953.9),

(63,1909.0),

(64,1975.8),

(65,1924.0),

(66,1901.1),

(67,1800.6),

(68,1891.8),

(69,1820.9),

(70,1676.6),

(71,1785.0),

(72,1689.2),

(73,1807.8),

(74,1830.0),

(75,1880.9),

(76,1846.1),

(77,1902.8),

(78,1940.1),

(79,1885.8),

(80,1955.5),

(81,1900.1),

(82,1963.9),

(83,1949.7),

(84,1907.7),

(85,1918.8),

(86,1906.6),

(87,1997.6),

(88,2011.6),

(89,2043.0),

(90,2042.8),

(91,2168.9),

(92,2283.3),

(93,2307.7),

(94,2408.2),

(95,2375.0),

(96,2393.6),

(97,2328.1),

(98,2363.5),

(99,2399.4),

(100,2410.2),

(101,2376.0),

(102,2314.1),

(103,2372.7),

(104,2474.0),

(105,2286.0),

(106,2316.0),

(107,2317.8),

(108,2351.3),

(109,2367.6),

(110,2379.6),

(111,2409.0),

(112,2356.9),

(113,2367.9),

(114,2388.9),

(115,2409.8),

(116,2426.3),

(117,2449.3),

(118,2497.9),

(119,2446.7),

(120,2436.9),

(121,2421.9),

(122,2410.4),

(123,2401.1),

(124,2442.4),

(125,2471.0),

(126,2472.4),

(127,2478.4),

(128,2460.6),

(129,2483.0),

(130,2524.1),

(131,2600.9),

(132,2647.4),

(133,2558.0),

(134,2545.0),

(135,2572.7),

(136,2615.3),

(137,2641.0),

(138,2654.0),

(139,2675.0),

(140,2713.8),

(141,2764.4),

(142,2734.4),

(143,2754.6),

(144,2692.9),

(145,2680.4),

(146,2758.8),

(147,2878.7),

(148,2890.3),

(149,3057.0),

(150,3000.1),

(151,3081.1),

(152,3182.6),

(153,3200.0),

(154,3104.0),

(155,3084.0),

(156,3008.9),

(157,2999.9),

(158,2962.0),

(159,3196.8),

(160,3138.3),

(161,3099.9),

(162,2986.6),

(163,3008.9),

(164,3055.2),

(165,3000.3),

(166,3033.5),

(167,3051.9),

(168,3164.7),

(169,3111.9),

(170,3138.8),

(171,3205.0),

(172,3225.0),

(173,3167.5),

(174,3148.2),

(175,3080.7),

(176,3162.2),

(177,3161.0),

(178,3148.0),

(179,3182.4),

(180,3312.5),

(181,3260.5),

(182,3297.4),

(183,3284.7),

(184,3307.5),

(185,3346.5),

(186,3441.9),

(187,3400.0),

(188,3401.8),

(189,3451.0),

(190,3499.1),

(191,3531.4),

(192,3368.0),

(193,3294.6),

(194,3149.8),

(195,3268.6),

(196,3175.1),

(197,3116.2),

(198,3103.0),

(199,3156.1),

(200,3078.1),

(201,3008.7),

(202,2954.9),

(203,2960.5),

(204,3129.0),

(205,2999.9),

(206,3019.8),

(207,3095.1),

(208,3174.1),

(209,3144.9),

(210,3148.7),

(211,3221.3),

(212,3125.0),

(213,3199.2),

(214,3100.0),

(215,3195.7),

(216,3190.6),

(217,3286.6),

(218,3442.9),

(219,3443.6),

(220,3363.7),

(221,3338.6),

(222,3272.7),

(223,3207.2),

(224,3217.0),

(225,3184.9),

(226,3176.4),

(227,3204.4),

(228,3207.0),

(229,3286.3),

(230,3162.8),

(231,3211.0),

(232,3036.1),

(233,3004.5),

(234,3048.4),

(235,3241.2),

(236,3322.0),

(237,3311.4),

(238,3143.7),

(239,3035.0),

(240,3137.4),

(241,3110.3),

(242,3128.8),

(243,3131.1),

(244,3135.7),

(245,3105.5),

(246,3117.0),

(247,3099.4),

(248,3098.4),

(249,3118.1),

(250,3185.1),

(251,3195.3),

(252,3168.0),

(253,3220.1),

(254,3203.5),

(255,3186.7),

(256,3162.6),

(257,3158.0),

(258,3177.3),

(259,3104.2),

(260,3101.5),

(261,3116.4),

(262,3157.0),

(263,3165.1),

(264,3241.0),

(265,3236.1),

(266,3201.6),

(267,3206.2),

(268,3206.5),

(269,3185.3),

(270,3172.7),

(271,3284.0),

(272,3322.0),

(273,3285.9),

(274,3256.9),

(275,3186.6),

(276,3218.5)])

# get x and y vectors

x = points[:,0]

y = points[:,1]

# calculate polynomial

#z = np.polyfit(x, y, 3)

#f = np.poly1d(z)

###########

#x = np.array([0.0, 1.0, 2.0, 3.0,  4.0,  5.0])

#y = np.array([0.0, 0.8, 0.9, 0.1, -0.8, -1.0])

z = np.polyfit(x, y, 3)

print("z=")

print(z)

p = np.poly1d(z)

print("np.poly1d(z)=")

print(p)

print("p(0.5) =")

print(p(0.5))

print("p(3.5)) =")

print(p(3.5))

print("p(10) =")

print(p(10))

warnings.simplefilter('ignore', np.RankWarning)

p30 = np.poly1d(np.polyfit(x, y, 30))

print("p30 = np.poly1d(np.polyfit(x, y, 30)) =")

print(p30)

print("p30(4) =")

print(p30(4))

print("p30(5) =")

print(p30(5))

print("p30(4.5) =")

print(p30(4.5))

#xp = np.linspace(-2, 6, 100)

xp = np.linspace(x[0], x[-1], 50)

_ = plt.plot(x, y, '.', xp, p(xp), '-', xp, p30(xp), '--')

#plt.ylim(-2,2)

plt.xlim([x[0]-1, x[-1] + 1 ])

plt.show()

#x_new = np.linspace(x[0], x[-1], 50)

#y_new = f(x_new)

#plt.plot(x,y,'o', x_new, y_new)

#plt.xlim([x[0]-1, x[-1] + 1 ])

#plt.show()

#points = np.array([(1, 1), (2, 4), (3, 1), (9, 3)])

# get x and y vectors

#x = points[:,0]

#y = points[:,1]

# calculate polynomial

#z = np.polyfit(x, y, 3)

#f = np.poly1d(z)

# calculate new x's and y's

#x_new = np.linspace(x[0], x[-1], 50)

#y_new = f(x_new)

#plt.plot(x,y,'o', x_new, y_new)

#plt.xlim([x[0]-1, x[-1] + 1 ])

#plt.show()

+++++++++++++++++++++

C:\pythonPRACTICA>python amazonpoli7.py

z=

[-3.34784417e-04  1.24298536e-01 -4.62834888e+00  1.85664534e+03]

np.poly1d(z)=

            3          2

-0.0003348 x + 0.1243 x - 4.628 x + 1857

p(0.5) =

1854.3621959174566

p(3.5)) =

1841.9544196631816

p(10) =

1822.4569179179982

p30 = np.poly1d(np.polyfit(x, y, 30)) =

            30             29             28             27

-1.444e-61 x  + 2.055e-58 x  - 9.645e-56 x  + 7.731e-54 x

              26            25             24             23

 + 5.449e-51 x  - 3.02e-49 x  - 3.909e-46 x  - 2.582e-44 x

              22             21             20             19

 + 2.382e-41 x  + 5.378e-39 x  - 8.957e-37 x  - 5.213e-34 x

              18             17             16             15

 - 6.871e-33 x  + 3.711e-29 x  + 4.205e-27 x  - 2.399e-24 x

              14             13             12             11

 - 3.789e-22 x  + 1.779e-19 x  + 1.235e-17 x  - 1.416e-14 x

              10             9             8             7

 + 2.913e-12 x  - 2.911e-10 x + 1.242e-08 x + 3.669e-07 x

              6            5          4         3         2

 - 7.651e-05 x + 0.004296 x - 0.1236 x + 1.868 x - 12.89 x + 29.4 x + 1755

p30(4) =

1758.3889495399844

p30(5) =

1748.325647242414

p30(4.5) =

1753.1670544079063

++++++++++

4,40,60

+++++++++++++++++++

C:\pythonPRACTICA>python amazonpoli8.py

z=

[ 9.58312992e-07 -8.65689815e-04  2.18952069e-01 -1.04794573e+01

  1.93900151e+03]

np.poly1d(z)=

           4             3         2

9.583e-07 x - 0.0008657 x + 0.219 x - 10.48 x + 1939

p(0.5) =

1933.8164076661278

p(3.5)) =

1904.9685961899124

p(10) =

1855.2460339175325

p30 = np.poly1d(np.polyfit(x, y, 30)) =

           40             39             38            37

3.043e-85 x  - 3.241e-82 x  + 8.306e-80 x  + 1.39e-77 x

              36             35             34            33

 - 3.728e-75 x  - 1.478e-72 x  - 6.023e-71 x  + 8.61e-68 x

              32             31             30             29

 + 2.673e-65 x  + 1.346e-63 x  - 1.525e-60 x  - 5.484e-58 x

              28             27             26             25

 - 5.322e-56 x  + 2.431e-53 x  + 1.126e-50 x  + 1.539e-48 x

              24             23             22             21

 - 3.938e-46 x  - 2.285e-43 x  - 3.316e-41 x  + 8.673e-39 x

            20             19            18             17

 + 4.7e-36 x  + 4.168e-34 x  - 2.77e-31 x  - 8.317e-29 x

              16             15             14            13

 + 9.127e-27 x  + 7.605e-24 x  - 2.138e-22 x  - 6.13e-19 x

              12             11             10            9

 + 5.358e-17 x  + 4.235e-14 x  - 1.541e-11 x  + 2.68e-09 x

              8             7            6           5          4

 - 2.928e-07 x + 2.156e-05 x - 0.001087 x + 0.03706 x - 0.8215 x

          3         2

 + 11.06 x - 80.33 x + 256.5 x + 1529

p30(4) =

1800.793366248045

p30(5) =

1772.5089961620001

p30(4.5) =

1787.4067003460548

++++++++++++++++++++++++++++++++

# get x and y vectors

x = points[:,0]

y = points[:,1]

# calculate polynomial

#z = np.polyfit(x, y, 3)

#f = np.poly1d(z)

###########

#x = np.array([0.0, 1.0, 2.0, 3.0,  4.0,  5.0])

#y = np.array([0.0, 0.8, 0.9, 0.1, -0.8, -1.0])

z = np.polyfit(x, y, 10)

print("z=")

print(z)

p = np.poly1d(z)

print("np.poly1d(z)=")

print(p)

print("p(0.5) =")

print(p(0.5))

print("p(3.5)) =")

print(p(3.5))

print("p(10) =")

print(p(10))

warnings.simplefilter('ignore', np.RankWarning)

p30 = np.poly1d(np.polyfit(x, y, 100))

print("p30 = np.poly1d(np.polyfit(x, y, 30)) =")

print(p30)

print("p30(4) =")

print(p30(4))

print("p30(5) =")

print(p30(5))

print("p30(4.5) =")

print(p30(4.5))

#xp = np.linspace(-2, 6, 100)

xp = np.linspace(x[0], x[-1], 70)

_ = plt.plot(x, y, '.', xp, p(xp), '-', xp, p30(xp), '--')

#plt.ylim(-2,2)

plt.xlim([x[0]-1, x[-1] + 1 ])

plt.show()

#################

PREDICCION ON 6 D ENERO

Y AL 21

SE VE

z = np.polyfit(x, y, 20)

print("z=")

print(z)

p = np.poly1d(z)

print("np.poly1d(z)=")

print(p)

print("p(0.5) =")

print(p(0.5))

print("p(3.5)) =")

print(p(3.5))

print("p(10) =")

print(p(10))

warnings.simplefilter('ignore', np.RankWarning)

p30 = np.poly1d(np.polyfit(x, y, 200))

print("p30 = np.poly1d(np.polyfit(x, y, 30)) =")

print(p30)

para valores 20, 200,  o 200, 1000

levanta el error

C:\pythonPRACTICA>python amazonpoli10.py

sys:1: RankWarning: Polyfit may be poorly conditioned

z=

[-1.76756035e-37  3.58223469e-34 -3.06497957e-31  1.36758359e-28

 -2.81535807e-26 -1.66530926e-24  2.32319154e-21 -3.94403175e-19

 -7.46606724e-17  5.07326718e-14 -1.25076105e-11  1.90383040e-09

 -1.97577325e-07  1.43460146e-05 -7.25954736e-04  2.49873712e-02

 -5.59107152e-01  7.54733906e+00 -5.41191275e+01  1.66574675e+02

  1.62003872e+03]

np.poly1d(z)=

            20             19             18             17

-1.768e-37 x  + 3.582e-34 x  - 3.065e-31 x  + 1.368e-28 x

              16             15             14             13

 - 2.815e-26 x  - 1.665e-24 x  + 2.323e-21 x  - 3.944e-19 x

              12             11             10             9

 - 7.466e-17 x  + 5.073e-14 x  - 1.251e-11 x  + 1.904e-09 x

              8             7            6           5          4

 - 1.976e-07 x + 1.435e-05 x - 0.000726 x + 0.02499 x - 0.5591 x

          3         2

 + 7.547 x - 54.12 x + 166.6 x + 1620

p(0.5) =

1690.7055204099

p(3.5)) =

1791.6592544942705

p(10) =

1728.4088095616235

C:\Users\roberto.martinez\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\lib\polynomial.py:627: RuntimeWarning: overflow encountered in multiply

  scale = NX.sqrt((lhs*lhs).sum(axis=0))

C:\Users\roberto.martinez\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\core\_methods.py:47: RuntimeWarning: overflow encountered in reduce

  return umr_sum(a, axis, dtype, out, keepdims, initial, where)

C:\Users\roberto.martinez\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\lib\polynomial.py:628: RuntimeWarning: invalid value encountered in true_divide

  lhs /= scale

 ** On entry to DLASCLS parameter number  4 had an illegal value

 ** On entry to DLASCLS parameter number  4 had an illegal value

Traceback (most recent call last):

  File "C:\pythonPRACTICA\amazonpoli10.py", line 310, in <module>

    p30 = np.poly1d(np.polyfit(x, y, 200))

  File "<__array_function__ internals>", line 5, in polyfit

  File "C:\Users\roberto.martinez\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\lib\polynomial.py", line 629, in polyfit

    c, resids, rank, s = lstsq(lhs, rhs, rcond)

  File "<__array_function__ internals>", line 5, in lstsq

  File "C:\Users\roberto.martinez\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\linalg\linalg.py", line 2306, in lstsq

    x, resids, rank, s = gufunc(a, b, rcond, signature=signature, extobj=extobj)

  File "C:\Users\roberto.martinez\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\linalg\linalg.py", line 100, in _raise_linalgerror_lstsq

    raise LinAlgError("SVD did not converge in Linear Least Squares")

numpy.linalg.LinAlgError: SVD did not converge in Linear Least Squares

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

FIRST STEP

con librerias

amzn = pdr.get_data_yahoo('AMZN', 

                          start=datetime.datetime(2019, 12, 1), 

                          end=datetime.datetime(2021, 1, 7))

  

#Import numpy as np import numpy as np

# Assign `Adj close to "daily_close 

daily_close = amzn[['Adj Close']]

# Daily returns 

daily_pct_change = daily_close.pct_change()

# Replace NA values with a 

daily_pct_change.fillna(0, inplace=True)

# Inspect daily returns 

print(daily_pct_change)

# Daily log returns 

daily_log_returns = np.log(daily_close.pct_change() +1)

# Print daily log returns 

print(daily_log_returns)

# Resample "amzn" to business months, take last observation as value 

monthly = amzn.resample('BM').apply(lambda x: x[-1])

# Calculate the monthly percentage change 

monthly.pct_change()

# Resample amzn" to quarters, take the mean as value per quarter 

quarter = amzn.resample("4M").mean()

# Calculate the quarterly percentage change 

quarter.pct_change()

# Import matplotlib import matplotlib.pyplot as plt

# Plot the distribution of daily_pct_c 

daily_pct_change.hist(bins=50)

# Show the plot 

plt.show()

# Pull up summary statistics

print("daily_pct_change.describe()") 

print(daily_pct_change.describe())

# Calculate the cumulative daily returns 

cum_daily_return = (1 + daily_pct_change).cumprod()

# Print 'cum_daily_return 

print(cum_daily_return)

# Import matplotlib import matplotlib.pyplot as plt

# Plot the cumulative daily returns 

cum_daily_return.plot(figsize=(12,8))

# Show the plot I 

plt.show()

# Resample the cumulative daily return to cumulative monthly return ? 

cum_monthly_return = cum_daily_return.resample("M").mean()

# Print the 'cum_monthly_return 

print(cum_monthly_return)

cum_monthly_return.plot(figsize=(12,8))

# Show the plot I 

plt.show()

python definitve1.py

            Adj Close

Date

2019-12-02   0.000000

2019-12-03  -0.006533

2019-12-04  -0.005237

2019-12-05  -0.011478

2019-12-06   0.006389

...               ...

2020-12-31  -0.008801

2021-01-04  -0.021585

2021-01-05   0.010004

2021-01-06  -0.024897

2021-01-07   0.019867

[278 rows x 1 columns]

            Adj Close

Date

2019-12-02        NaN

2019-12-03  -0.006555

2019-12-04  -0.005251

2019-12-05  -0.011545

2019-12-06   0.006369

...               ...

2020-12-31  -0.008840

2021-01-04  -0.021821

2021-01-05   0.009955

2021-01-06  -0.025212

2021-01-07   0.019672

[278 rows x 1 columns]

daily_pct_change.describe()

        Adj Close

count  278.000000

mean     0.002383

std      0.023477

min     -0.079221

25%     -0.009576

50%      0.001987

75%      0.014116

max      0.079295

            Adj Close

Date

2019-12-02   1.000000

2019-12-03   0.993467

2019-12-04   0.988263

2019-12-05   0.976920

2019-12-06   0.983161

...               ...

2020-12-31   1.828093

2021-01-04   1.788634

2021-01-05   1.806528

2021-01-06   1.761551

2021-01-07   1.796548

[278 rows x 1 columns]

            Adj Close

Date

2019-12-31   1.002342

2020-01-31   1.057610

2020-02-29   1.159730

2020-03-31   1.050915

2020-04-30   1.250957

2020-05-31   1.343839

2020-06-30   1.466965

2020-07-31   1.714107

2020-08-31   1.823785

2020-09-30   1.774107

2020-10-31   1.813314

2020-11-30   1.763476

2020-12-31   1.794875

2021-01-31   1.788315

VECTORS, INITIAL CLASS

PYTHON APLICACIONES FINANCIERAS, import pandas_datareader as pdr

primeri importate

aapl = pdr.get_data_yahoo('AAPL', 

                          start=datetime.datetime(2006, 10, 1), 

                          end=datetime.datetime(2012, 1, 1))

# Return first rows of `aapl`

aapl.head()

# Return last rows of `aapl`

aapl.tail()

# Describe `aapl`

aapl.describe()

aapl.to_csv('./aapl_oh2c.csv')

df = pd.read_csv('./aapl_oh2c.csv', header=0, index_col='Date', parse_dates=True)

******************

APPL  

todas ocupan las librerias

import pandas_datareader as pdr

import datetime

import pandas as pd

import matplotlib.pyplot as plt

APPL

AMZN

avance 1

AMZN

ANALISIS 1

up today

# Import matplotlib

import matplotlib.pyplot as plt 

# Isolate the `Adj Close` values and transform the DataFrame

daily_close_px = all_data[['Adj Close']].reset_index().pivot('Date', 'Ticker', 'Adj Close')

# Calculate the daily percentage change for `daily_close_px`

daily_pct_change = daily_close_px.pct_change()

# Plot the distributions

daily_pct_change.hist(bins=50, sharex=True, figsize=(12,8))

# Show the resulting plot

plt.show()

********************************

tickers1withplot00SCATTER.py:46: FutureWarning: pandas.scatter_matrix is deprecated, use pandas.plotting.scatter_matrix instead

  pd.scatter_matrix(daily_pct_change, diagonal='kde', alpha=0.1,figsize=(12,12))

New Books on my link

analysis en 1-5-2021

print("2006 to 2012")     

tickers = ['AMZN', 'MSFT', 'TSLA', 'GOOG'] 

all_data = get(tickers, datetime.datetime(2006, 10, 1), datetime.datetime(2012, 1, 1))

# Import matplotlib import matplotlib.pyplot as plt

# Isolate the 'Adj close' values and transform the DataFrame 

daily_close_px = all_data[['Adj Close']].reset_index().pivot('Date','Ticker', 'Adj Close')

# Calculate the daily percentage change for daily_close_px' 

daily_pct_change = daily_close_px.pct_change()

# Plot the distributions 

daily_pct_change.hist(bins=50, sharex=True, figsize=(12,8))

# Show the resulting plot 

#plt.xlabel('Smarts')

#plt.ylabel('Probability')

plt.title('Calculate the daily percentage change for daily_close_px 2006 to 2012')

plt.show()

# Plot a scatter matrix with the daily_pct_change data 

pd.plotting.scatter_matrix(daily_pct_change, diagonal='kde', alpha=0.1)

# pd.scatter_matrix(daily_pct_change, diagonal='kde', alpha=0.1,figsize(12,12))

#plt.xlabel('Smarts')

#plt.ylabel('Probability')

plt.title('Plot a scatter matrix with the daily_pct_change data 2006 to 2012')

msft = pdr.get_data_yahoo('MSFT', 

                          start=datetime.datetime(2019, 12, 1), 

                          end=datetime.datetime(2021, 1, 4))

                          

#Inspect the index                 

msft.index

#Inspect the columns

msft.columns

#Select only the last 10 observationes of Close

ts= msft['Close'][-10:]

#Check the type of 'ts'

type(ts)

#Inspect the fisrt rows of November-december 2020

print(msft.loc[pd.Timestamp('2019-11-01'):pd.Timestamp('2021-01-04')].head())

#Inspect the first rows of 2020

print(msft.loc['2020'].head())

#Inspect the first rows of 2020

print(msft.iloc[22:43])

# Return first rows of `msft`

msft.head()

# Return last rows of `msft`

msft.tail()

# Describe `msft`

msft.describe()

#Sample 20 rows

print("Sample 20 rows")

sample= msft.sample(20)

#resample to monthly level

print("resample to monthly level")

monthly_msft = msft.resample('M').mean()

#Print 'monthly_msft'

print("monthly_msft")

print(monthly_msft)

#Add a column 'diff' to 'msft'

msft['diff']= msft.Open - msft.Close

print(msft['diff']) 

#imprime al archivo

msft.to_csv('./msft_oh4c.csv')

#lee del archivo

df = pd.read_csv('./msft_oh4c.csv', header=0, index_col='Date', parse_dates=True)

# Plot the closing prices for `msft`

msft['Close'].plot(grid=True)

# Show the plot

plt.title('MSFT 2019-2021 close prices')

plt.show()

plt.title('MSFT 2019-2021 close prices  diferencias')

msft['diff'].plot(grid=True)

plt.show()

second para varias

def get(tickers, startdate, enddate): 

    def data(ticker):

      return (pdr.get_data_yahoo(ticker, start=startdate, end=enddate))

    datas = map (data, tickers) 

    return(pd.concat(datas, keys=tickers, names=['Ticker', 'Date']))

print("2006 to 2012")     

tickers = ['AMZN', 'MSFT', 'TSLA', 'GOOG'] 

all_data = get(tickers, datetime.datetime(2012, 10, 1), datetime.datetime(2021, 1, 1))

# Import matplotlib import matplotlib.pyplot as plt

# Isolate the 'Adj close' values and transform the DataFrame 

daily_close_px = all_data[['Adj Close']].reset_index().pivot('Date','Ticker', 'Adj Close')

# Calculate the daily percentage change for daily_close_px' 

daily_pct_change = daily_close_px.pct_change()

# Plot the distributions 

daily_pct_change.hist(bins=50, sharex=True, figsize=(12,8))

# Show the resulting plot 

#plt.xlabel('Smarts')

#plt.ylabel('Probability')

plt.title('Calculate the daily percentage change for daily_close_px 2012 to 2021')

plt.show()

# Plot a scatter matrix with the daily_pct_change data 

pd.plotting.scatter_matrix(daily_pct_change, diagonal='kde', alpha=0.1)

# pd.scatter_matrix(daily_pct_change, diagonal='kde', alpha=0.1,figsize(12,12))

#plt.xlabel('Smarts')

#plt.ylabel('Probability')

plt.title('Plot a scatter matrix with the daily_pct_change data 2012 to 2021')

print("2006 to 2012")  

plt.show()

amzn = pdr.get_data_yahoo('AMZN', 

                          start=datetime.datetime(2019, 12, 1), 

                          end=datetime.datetime(2021, 1, 5))

  

#Import numpy as np import numpy as np

# Assign `Adj close to "daily_close 

daily_close = amzn[['Adj Close']]

# Daily returns 

daily_pct_change = daily_close.pct_change()

# Replace NA values with a 

daily_pct_change.fillna(0, inplace=True)

# Inspect daily returns 

print(daily_pct_change)

# Daily log returns 

daily_log_returns = np.log(daily_close.pct_change() +1)

# Print daily log returns 

print(daily_log_returns)

# Resample "amzn" to business months, take last observation as value 

monthly = amzn.resample('BM').apply(lambda x: x[-1])

# Calculate the monthly percentage change 

monthly.pct_change()

# Resample amzn" to quarters, take the mean as value per quarter 

quarter = amzn.resample("4M").mean()

# Calculate the quarterly percentage change 

quarter.pct_change()

# Import matplotlib import matplotlib.pyplot as plt

# Plot the distribution of daily_pct_c 

daily_pct_change.hist(bins=50)

# Show the plot 

plt.show()

# Pull up summary statistics

print("daily_pct_change.describe()") 

print(daily_pct_change.describe())

# Calculate the cumulative daily returns 

cum_daily_return = (1 + daily_pct_change).cumprod()

# Print 'cum_daily_return 

print(cum_daily_return)

# Import matplotlib import matplotlib.pyplot as plt

# Plot the cumulative daily returns 

cum_daily_return.plot(figsize=(12,8))

# Show the plot I 

plt.show()

# Resample the cumulative daily return to cumulative monthly return ? 

cum_monthly_return = cum_daily_return.resample("M").mean()

# Print the 'cum_monthly_return 

print(cum_monthly_return)

cum_monthly_return.plot(figsize=(12,8))

# Show the plot I 

plt.show()

desde cero computdora sin nada, pongo python abre microsoft store bajo la ultima version y ejecuto 

C:\Users>cd rober

C:\Users\rober>pyhton PYTHON1.PY

'pyhton' is not recognized as an internal or external command,

operable program or batch file.

C:\Users\rober>python PYTHON1.PY

Traceback (most recent call last):

  File "C:\Users\rober\PYTHON1.PY", line 1, in <module>

    import pandas_datareader as pdr

ModuleNotFoundError: No module named 'pandas_datareader'

C:\Users\rober>python PYTHON1.PY

C:\Users\rober>dir

 Volume in drive C has no label.

 Volume Serial Number is D08A-3849

 Directory of C:\Users\rober

12/26/2020  02:29 PM    <DIR>          .

12/26/2020  02:29 PM    <DIR>          ..

10/03/2020  09:15 PM    <DIR>          .android

10/16/2020  08:35 PM    <DIR>          .cisco

10/03/2020  09:56 PM    <DIR>          .eclipse

12/26/2020  01:27 PM    <DIR>          .idlerc

12/16/2020  02:30 PM    <DIR>          .openshot_qt

12/22/2020  11:23 AM    <DIR>          .p2

10/03/2020  09:56 PM    <DIR>          .tooling

12/10/2020  12:43 AM    <DIR>          3D Objects

12/26/2020  02:29 PM           149,416 aapl_oh2c.csv

12/10/2020  12:44 AM    <DIR>          Contacts

12/26/2020  02:25 PM    <DIR>          Desktop

12/26/2020  01:14 PM    <DIR>          Documents

12/26/2020  02:24 PM    <DIR>          Downloads

10/03/2020  09:34 PM    <DIR>          eclipse

10/03/2020  09:59 PM    <DIR>          eclipse-workspace

10/04/2020  07:49 PM    <DIR>          eclipse-workspace2

10/04/2020  08:30 PM    <DIR>          eclipse-workspace3

10/04/2020  09:08 PM    <DIR>          eclipse-workspace4

10/04/2020  09:49 PM    <DIR>          eclipse-workspace5

12/10/2020  12:44 AM    <DIR>          Favorites

10/04/2020  09:52 PM    <DIR>          IdeaProjects

09/26/2020  12:21 AM    <DIR>          Intel

12/10/2020  12:44 AM    <DIR>          Links

12/15/2020  03:08 PM    <DIR>          Music

12/16/2020  02:17 PM    <DIR>          OneDrive

11/22/2020  03:11 PM    <DIR>          Oracle

12/19/2020  01:25 PM    <DIR>          Pictures

12/16/2020  11:46 AM       110,000,798 prian.mp4

12/24/2020  04:51 PM               128 PUTTY.RND

12/26/2020  02:28 PM               477 PYTHON1.PY

12/10/2020  12:44 AM    <DIR>          Saved Games

12/10/2020  12:44 AM    <DIR>          Searches

12/12/2020  05:33 PM     5,414,812,143 Untitled Project.mp4

12/10/2020  12:44 AM    <DIR>          Videos

               5 File(s)  5,524,962,962 bytes

              31 Dir(s)  10,117,238,784 bytes free

C:\Users\rober>pip install matplotlib

Collecting matplotlib

  Downloading matplotlib-3.3.3-cp39-cp39-win_amd64.whl (8.5 MB)

     |████████████████████████████████| 8.5 MB 36 kB/s

Collecting pillow>=6.2.0

  Downloading Pillow-8.0.1-cp39-cp39-win_amd64.whl (2.1 MB)

     |████████████████████████████████| 2.1 MB 192 kB/s

Requirement already satisfied: python-dateutil>=2.1 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from matplotlib) (2.8.1)

Requirement already satisfied: numpy>=1.15 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from matplotlib) (1.19.4)

Collecting kiwisolver>=1.0.1

  Downloading kiwisolver-1.3.1-cp39-cp39-win_amd64.whl (51 kB)

     |████████████████████████████████| 51 kB 68 kB/s

Collecting pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3

  Downloading pyparsing-2.4.7-py2.py3-none-any.whl (67 kB)

     |████████████████████████████████| 67 kB 622 kB/s

Collecting cycler>=0.10

  Downloading cycler-0.10.0-py2.py3-none-any.whl (6.5 kB)

Requirement already satisfied: six>=1.5 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from python-dateutil>=2.1->matplotlib) (1.15.0)

Installing collected packages: pillow, kiwisolver, pyparsing, cycler, matplotlib

Successfully installed cycler-0.10.0 kiwisolver-1.3.1 matplotlib-3.3.3 pillow-8.0.1 pyparsing-2.4.7

WARNING: You are using pip version 20.2.3; however, version 20.3.3 is available.

You should consider upgrading via the 'C:\Users\rober\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\python.exe -m pip install --upgrade pip' command.

C:\Users\rober>pip install scipy

Collecting scipy

  Downloading scipy-1.5.4-cp39-cp39-win_amd64.whl (31.4 MB)

     |████████████████████████████████| 31.4 MB 97 kB/s

Requirement already satisfied: numpy>=1.14.5 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from scipy) (1.19.4)

Installing collected packages: scipy

Successfully installed scipy-1.5.4

WARNING: You are using pip version 20.2.3; however, version 20.3.3 is available.

You should consider upgrading via the 'C:\Users\rober\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\python.exe -m pip install --upgrade pip' command.

C:\Users\rober>pip install numpy

Requirement already satisfied: numpy in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (1.19.4)

WARNING: You are using pip version 20.2.3; however, version 20.3.3 is available.

You should consider upgrading via the 'C:\Users\rober\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\python.exe -m pip install --upgrade pip' command.

C:\Users\rober>python AMZNclosing

ft Windows [Version 10.0.18363.1256]

(c) 2019 Microsoft Corporation. All rights reserved.

C:\Users\rober>PYTHON

C:\Users\rober>python

C:\Users\rober>pip

Usage:

  C:\Users\rober\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\python.exe -m pip <command> [options]

Commands:

  install                     Install packages.

  download                    Download packages.

  uninstall                   Uninstall packages.

  freeze                      Output installed packages in requirements format.

  list                        List installed packages.

  show                        Show information about installed packages.

  check                       Verify installed packages have compatible dependencies.

  config                      Manage local and global configuration.

  search                      Search PyPI for packages.

  cache                       Inspect and manage pip's wheel cache.

  wheel                       Build wheels from your requirements.

  hash                        Compute hashes of package archives.

  completion                  A helper command used for command completion.

  debug                       Show information useful for debugging.

  help                        Show help for commands.

General Options:

  -h, --help                  Show help.

  --isolated                  Run pip in an isolated mode, ignoring environment variables and user configuration.

  -v, --verbose               Give more output. Option is additive, and can be used up to 3 times.

  -V, --version               Show version and exit.

  -q, --quiet                 Give less output. Option is additive, and can be used up to 3 times (corresponding to

                              WARNING, ERROR, and CRITICAL logging levels).

  --log <path>                Path to a verbose appending log.

  --no-input                  Disable prompting for input.

  --proxy <proxy>             Specify a proxy in the form [user:passwd@]proxy.server:port.

  --retries <retries>         Maximum number of retries each connection should attempt (default 5 times).

  --timeout <sec>             Set the socket timeout (default 15 seconds).

  --exists-action <action>    Default action when a path already exists: (s)witch, (i)gnore, (w)ipe, (b)ackup,

                              (a)bort.

  --trusted-host <hostname>   Mark this host or host:port pair as trusted, even though it does not have valid or any

                              HTTPS.

  --cert <path>               Path to alternate CA bundle.

  --client-cert <path>        Path to SSL client certificate, a single file containing the private key and the

                              certificate in PEM format.

  --cache-dir <dir>           Store the cache data in <dir>.

  --no-cache-dir              Disable the cache.

  --disable-pip-version-check

                              Don't periodically check PyPI to determine whether a new version of pip is available for

                              download. Implied with --no-index.

  --no-color                  Suppress colored output

  --no-python-version-warning

                              Silence deprecation warnings for upcoming unsupported Pythons.

  --use-feature <feature>     Enable new functionality, that may be backward incompatible.

  --use-deprecated <feature>  Enable deprecated functionality, that will be removed in the future.

C:\Users\rober>pip install pandas

Collecting pandas

  Downloading pandas-1.2.0-cp39-cp39-win_amd64.whl (9.3 MB)

     |████████████████████████████████| 9.3 MB 3.2 MB/s

Collecting numpy>=1.16.5

  Downloading numpy-1.19.4-cp39-cp39-win_amd64.whl (13.0 MB)

     |████████████████████████████████| 13.0 MB 80 kB/s

Collecting pytz>=2017.3

  Downloading pytz-2020.5-py2.py3-none-any.whl (510 kB)

     |████████████████████████████████| 510 kB 3.3 MB/s

Collecting python-dateutil>=2.7.3

  Downloading python_dateutil-2.8.1-py2.py3-none-any.whl (227 kB)

     |████████████████████████████████| 227 kB 2.2 MB/s

Collecting six>=1.5

  Downloading six-1.15.0-py2.py3-none-any.whl (10 kB)

Installing collected packages: numpy, pytz, six, python-dateutil, pandas

  WARNING: The script f2py.exe is installed in 'C:\Users\rober\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\Scripts' which is not on PATH.

  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.

Successfully installed numpy-1.19.4 pandas-1.2.0 python-dateutil-2.8.1 pytz-2020.5 six-1.15.0

WARNING: You are using pip version 20.2.3; however, version 20.3.3 is available.

You should consider upgrading via the 'C:\Users\rober\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\python.exe -m pip install --upgrade pip' command.

C:\Users\rober>pip install pandas_datareader

Collecting pandas_datareader

  Downloading pandas_datareader-0.9.0-py3-none-any.whl (107 kB)

     |████████████████████████████████| 107 kB 3.3 MB/s

Requirement already satisfied: pandas>=0.23 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from pandas_datareader) (1.2.0)

Collecting requests>=2.19.0

  Downloading requests-2.25.1-py2.py3-none-any.whl (61 kB)

     |████████████████████████████████| 61 kB 1.9 MB/s

Collecting lxml

  Downloading lxml-4.6.2-cp39-cp39-win_amd64.whl (3.5 MB)

     |████████████████████████████████| 3.5 MB 6.8 MB/s

Requirement already satisfied: python-dateutil>=2.7.3 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from pandas>=0.23->pandas_datareader) (2.8.1)

Requirement already satisfied: pytz>=2017.3 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from pandas>=0.23->pandas_datareader) (2020.5)

Requirement already satisfied: numpy>=1.16.5 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from pandas>=0.23->pandas_datareader) (1.19.4)

Collecting certifi>=2017.4.17

  Downloading certifi-2020.12.5-py2.py3-none-any.whl (147 kB)

     |████████████████████████████████| 147 kB 6.8 MB/s

Collecting idna<3,>=2.5

  Downloading idna-2.10-py2.py3-none-any.whl (58 kB)

     |████████████████████████████████| 58 kB 161 kB/s

Collecting urllib3<1.27,>=1.21.1

  Downloading urllib3-1.26.2-py2.py3-none-any.whl (136 kB)

     |████████████████████████████████| 136 kB ...

Collecting chardet<5,>=3.0.2

  Downloading chardet-4.0.0-py2.py3-none-any.whl (178 kB)

     |████████████████████████████████| 178 kB 6.4 MB/s

Requirement already satisfied: six>=1.5 in c:\users\rober\appdata\local\packages\pythonsoftwarefoundation.python.3.9_qbz5n2kfra8p0\localcache\local-packages\python39\site-packages (from python-dateutil>=2.7.3->pandas>=0.23->pandas_datareader) (1.15.0)

Installing collected packages: certifi, idna, urllib3, chardet, requests, lxml, pandas-datareader

  WARNING: The script chardetect.exe is installed in 'C:\Users\rober\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\Scripts' which is not on PATH.

  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.

Successfully installed certifi-2020.12.5 chardet-4.0.0 idna-2.10 lxml-4.6.2 pandas-datareader-0.9.0 requests-2.25.1 urllib3-1.26.2

WARNING: You are using pip version 20.2.3; however, version 20.3.3 is available.

You should consider upgrading via the 'C:\Users\rober\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\python.exe -m pip install --upgrade pip' command.

C:\Users\rober>pytho closesAPPL.py

'pytho' is not recognized as an internal or external command,

operable program or batch file.

C:\Users\rober>python closesAPPL.py

Matplotlib is building the font cache; this may take a moment.

Traceback (most recent call last):

  File "C:\Users\rober\closesAPPL.py", line 5, in <module>

    aapl['Close'].plot(grid=True)

NameError: name 'aapl' is not defined

C:\Users\rober>python PYTHON1.PY

*****ACTUALIZACION 2023, FIX 

 

La solución esta aquí

https://stackoverflow.com/questions/71696014/pandas-datareader-not-able-to-pull-from-yahoo-finance-unable-to-read-url-with-r

 

Pandas-datareader not able to pull from yahoo finance- unable to read url with response text in error saying "our engineers are working on it"

Ask Question

Asked 10 months ago

Modified 9 months ago

Viewed 782 times

1

I was just working on a simple project trying to pull stock data from yahoo finance using pandas-datareader and the code send back an error which I will post below:

pandas_datareader._utils.RemoteDataError: Unable to read URL: https://finance.yahoo.com/quote/AAPL/history?period1=1577869200&period2=1648799999&interval=1d&frequency=1d&filter=history

Response Text:

b'<!DOCTYPE html>\n  <html lang="en-us"><head>\n  <meta http-equiv="content-type" content="text/html; charset=UTF-8">\n      <meta charset="utf-8">\n      <title>Yahoo</title>\n      <meta name="viewport" content="width=device-width,initial-scale=1,minimal-ui">\n      <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">\n      <style>\n  html {\n      height: 100%;\n  }\n  body {\n      background: #fafafc url(https://s.yimg.com/nn/img/sad-panda-201402200631.png) 50% 50%;\n      background-size: cover;\n      height: 100%;\n      text-align: center;\n      font: 300 18px "helvetica neue", helvetica, verdana, tahoma, arial, sans-serif;\n  }\n  table {\n      height: 100%;\n      width: 100%;\n      table-layout: fixed;\n      border-collapse: collapse;\n      border-spacing: 0;\n      border: none;\n  }\n  h1 {\n      font-size: 42px;\n      font-weight: 400;\n      color: #400090;\n  }\n  p {\n      color: #1A1A1A;\n  }\n  #message-1 {\n      font-weight: bold;\n      margin: 0;\n  }\n  #message-2 {\n      display: inline-block;\n      *display: inline;\n      zoom: 1;\n      max-width: 17em;\n      _width: 17em;\n  }\n      </style>\n  <script>\n    document.write(\'<img src="//geo.yahoo.com/b?s=1197757129&t=\'+new Date().getTime()+\'&src=aws&err_url=\'+encodeURIComponent(document.URL)+\'&err=%<pssc>&test=\'+encodeURIComponent(\'%<{Bucket}cqh[:200]>\')+\'" width="0px" height="0px"/>\');var beacon = new Image();beacon.src="//bcn.fp.yahoo.com/p?s=1197757129&t="+new Date().getTime()+"&src=aws&err_url="+encodeURIComponent(document.URL)+"&err=%<pssc>&test="+encodeURIComponent(\'%<{Bucket}cqh[:200]>\');\n  </script>\n  </head>\n  <body>\n  <!-- status code : 404 -->\n  <!-- Not Found on Server -->\n  <table>\n  <tbody><tr>\n      <td>\n      <img src="https://s.yimg.com/rz/p/yahoo_frontpage_en-US_s_f_p_205x58_frontpage.png" alt="Yahoo Logo">\n      <h1 style="margin-top:20px;">Will be right back...</h1>\n      <p id="message-1">Thank you for your patience.</p>\n      <p id="message-2">Our engineers are working quickly to resolve the issue.</p>\n      </td>\n  </tr>\n  </tbody></table>\n  </body></html>'

I looked all over forums to find a solution and saw this was a problem from July of 2021, but I am getting it now. I employed all the solutions, updating my pandas-datareader to make sure it was the right version, even pip uninstalling and pip installing all the packages and libraries again. Nothing seems to be working. No forums solutions work. Oddly enough when I run the scripts through command prompt it works and is able to pull data but not in my IDE which is Visual Studio Code. Does that mean the problem is with Visual Studio Code? Please help as this project is due very soon. I will keep monitoring this post to answer any follow up questions. Thanks!

• yahoo-finance
• pandas-datareader

Share

Improve this question

asked Mar 31, 2022 at 16:21

 

Jsingh22

1111 bronze badge

Add a comment

1 Answer

Sorted by:

                                                                                                  Highest score (default)                          Trending (recent votes count more)                          Date modified (newest first)                          Date created (oldest first)

0

There are fairly recent, open issues in the pandas datareader project regarding this error.

That is, the following snippet yields the observed errors:

from pandas_datareader import data as pdr

data = pdr.get_data_yahoo("SPY", start="2017-01-01", end="2017-04-30")

Here are two solutions. If you want to stick to the pandas datareader, you can try out the code below, which was adapted from this post:

from pandas_datareader import data as pdr

import yfinance as yf

yf.pdr_override()

# download dataframe using pandas_datareader

data = pdr.get_data_yahoo("SPY", start="2017-01-01", end="2017-04-30")

Or even easier, the pure yfinance version:

import yfinance as yf

data = yf.download("SPY", start="2017-01-01", end="2017-04-30")

Share

Improve this answer

 

 

La solución es

 

 

Aca esta el fix