2

我有以下数据：

import pandas as pd
from plotnine import *

gd_sp_tmp = pd.DataFrame({ '变量': {0: 'var1', 1: 'var1', 2: 'var1', 3: 'var1', 4: 'var1', 5: 'var1', 6: 'var1'，7：'var1'，8：'var1'，9：'var1'，10：'var1'，11：'var1'，12：'var1'，13：'var1'，14：'var1 ', 15: 'var1', 16: 'var1', 17: 'var1', 18: 'var1', 19: 'var1', 20: 'var1', 21: 'var1', 22: 'var1', 23：'var1'，24：'var1'，25：'var1'，26：'var1'，27：'var1'，28：'var1'，29：'var1'，30：'var1'，31： 'var1'，32：'var1'，33：'var1'，34：'var1'，35：'var1'，36：'var1'，37：'var1'，38：'var1'，39：'var1'，40：'var1'，41：'var1'，42：'var1'，43：'var1'，44：'var1' , 45: 'var1', 46: 'var1', 47: 'var1', 48: 'var1', 49: 'var1', 50: 'var2', 51: 'var2', 52: 'var2', 53 ：'var2'，54：'var2'，55：'var2'，56：'var2'，57：'var2'，58：'var2'，59：'var2'，60：'var2'，61：' var2'，62：'var2'，63：'var2'，64：'var2'，65：'var2'，66：'var2'，67：'var2'，68：'var2'，69：'var2' , 70: 'var2', 71: 'var2', 72: 'var2', 73: 'var2', 74:'var2'，75：'var2'，76：'var2'，77：'var2'，78：'var2'，79：'var2'，80：'var2'，81：'var2'，82：'var2 ', 83: 'var2', 84: 'var2', 85: 'var2', 86: 'var2', 87: 'var2', 88: 'var2', 89: 'var2', 90: 'var2', 91：'var2'，92：'var2'，93：'var2'，94：'var2'，95：'var2'，96：'var2'，97：'var2'，98：'var2'，99： 'var2'}, 'value': {0: 0.6058597809345508, 1: 0.5793863580299581, 2: 0.8464980992038321, 3: 0.24855227431181698, 4: 1.8852877490212698, 5: 0.4234171954404873, 6: 0.3435477323074209, 7: 3.358464370031963, 8: 0.5253401196517882, 9: 2.358632857360592, 10: 0.15960003602748035, 11: 0.2882705893127418, 12: 1.0995070639266127, 13: 0.3492611123700738, 14: 0.656410247866536, 15: 1.7926397942332677, 16: 0.2809984468410994, 17: 2.146319743864339, 18: 1.6912849075574694, 19: 1.233812138850312, 20: 0.21044290817060624, 21: 0.7130666643073327, 22: 0.521102906290718, 23: 0.8191663841868542, 24: 0.20231016020355008, 25: 1.542239677553837, 26: 0.07752167395995535, 27: 0.07661799644296931, 28: 0.13728522388491152, 29: 1.4268916808352554, 30: 1.2219293081314697, 31: 1.089318287649674, 32: 0.5889304040483466, 33: 3.871173476569569, 34: 0.2571045126240674, 35: 0.27332795371650104, 36: 1.2121464473427577, 37: 2.0229834870080117, 38: 0.5538327169626888, 39: 0.3354345395246616, 40: 0.39169801317212116, 41: 1.0415690828271393, 42: 0.9584774133158281, 43: 0.13738535777663943, 44: 1.874003757544322, 45: 1.7852374480589213, 46: 1.6370785639935181, 47: 0.8738310745465996, 48: 0.4777945179886022, 49: 0.7289840311727211, 50: 0.792295578​​4270402, 51: 0.9104711980757718, 52: 1.5561240516907253, 53: 0.3303774972464219, 54: 2.110632552079527, 55: 0.49383897345236455, 56: 0.5328351983603986, 57: 1.101045960316634, 58: 0.6511245820579645, 59: 1.1162218482680217, 60: 1.1528904383298124, 61: 0.34335972679097204, 62: 1.018800464369946, 63: 0.5416579415333236, 64: 1.214519609326636, 65: 0.23298089233642374, 66: 1.2353245009353024, 67: 0.41366066807689983, 68: 0.3922217060873213,69: 0.47724897903224234, 70: 1.2372675447604105, 71: 0.860009005949974, 72: 0.975115860544153, 73: 0.34103695692671854, 74: 3.715667756746576, 75: 0.8245813402150265, 76: 1.0146261204408322, 77: 1.429071625166872, 78: 1.1575801036803262, 79: 0.8892865356335216, 80: 1.4682387127243648, 81: 0.2790711201452777, 82: 0.21458250943662763, 83: 1.626193381231688, 84: 0.7862776167644395, 85: 0.8063680366888433, 86: 2.1349518016852866, 87: 0.16790682625128348, 88: 2.6898324320852316, 89: 3.1017929388719687, 90: 2.2161796611039484, 91: 0.27323366047568587, 92: 0.9876405202465337, 93: 0.5878226010690092, 94: 0.975411448085179, 95: 0.7933992437453187, 96: 1.3443593604932238, 97: 1.5392784611233619, 98: 1.1729165101630914, 99: 0.7643250100538129}}）

我创建以下直方图

plot_posterior_test = ggplot(data=gd_sp_tmp) + \
                           geom_histogram(aes(x='value', y='stat(density)')) + \
                           facet_wrap('~variable')

我想在这个图上添加一个lognormal分布的pdf scale = 0.8，其中包含所有图表。有什么想法我怎么能做到这一点？location = -0.5plotnine

4

1 回答 1

1

使用stat_function. 例如，给定您之前的代码，试试这个

import scipy.stats as stats

(ggplot(data=gd_sp_tmp)
 + geom_histogram(aes(x='value'))
 + stat_function(fun=stats.lognorm.pdf, args=dict(s=.95, loc=0.8, scale=-0.5))
 + facet_wrap('~variable')
)

您可以确保参数有意义，否则它们将计算为NaN值

于 2018-10-02T16:00:26.563 回答