Created
September 18, 2020 05:38
-
-
Save gyosit/001b8b5247fad393bb6476de57eaadc2 to your computer and use it in GitHub Desktop.
PD
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Gene: | |
def __init__(self, num, mins, maxs): | |
one_gene = np.ones(num) | |
set_gene = np.stack([one_gene, mins, maxs], axis=1) | |
init_gene = [x[0] * random.uniform(x[1], x[2]) for x in set_gene] | |
self.gene = init_gene | |
self.num = num | |
self.mins = mins | |
self.maxs = maxs | |
self.fitness = 0 | |
@classmethod | |
def getFitness(self, genes, model): | |
x = np.array([g.gene for g in genes]).reshape(-1, genes[0].num) | |
predicted = model.predict(x) | |
for i, p in enumerate(predicted): | |
genes[i].fitness = p | |
def getFitness_(self): | |
self.fitness = self.gene[0] - self.gene[1] | |
return self.fitness | |
def mutation(self, p=0.2): | |
r = random.randint(0, 10) | |
if(r <= p*10): | |
one_gene = np.ones(self.num) | |
set_gene = np.stack([one_gene, self.mins, self.maxs], axis=1) | |
init_gene = [x[0] * random.uniform(x[1], x[2]) for x in set_gene] | |
rand_i = random.randint(0, self.num-1) | |
self.gene[rand_i] = init_gene[rand_i] | |
@classmethod | |
def sortGene(self, genes, model): | |
self.getFitness(genes, model) | |
genes = sorted(genes, key=lambda g: g.fitness, reverse=True) | |
return genes | |
@classmethod | |
def select(self, genes): | |
l = int(len(genes)/4) | |
try: | |
return genes[:l] | |
except TypeError: | |
print("Removed the last gene") | |
genes.pop() | |
return genes[:l] | |
def cross(self, g1, g2): | |
rand_i = random.randint(1, g1.num-1) | |
g1_, g2_ = Gene(g1.num, g1.mins, g1.maxs), Gene(g1.num, g1.mins, g1.maxs) | |
f1, b1= g1.gene[:rand_i], g1.gene[rand_i:] | |
f2, b2= g2.gene[:rand_i], g2.gene[rand_i:] | |
g1_.gene, g2_.gene = f1 + b2, f2 + b1 | |
return [g1, g2, g1_, g2_] | |
@classmethod | |
def crossover(self, genes): | |
new_genes = [] | |
l = len(genes) | |
while(len(genes)*4 > len(new_genes)): | |
r1, r2 = random.randint(0,l-1), random.randint(0,l-1) | |
family = self.cross(self, genes[r1], genes[r2]) | |
new_genes += family | |
return new_genes |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Graphics(): | |
def dayPlot2D(self, startday, y, title, xlabel, ylabel): | |
row = y[1].shape[0] | |
col = 2 | |
data_range = pd.date_range(startday, periods=y[1].shape[1], freq='d') | |
plt.rcParams["font.size"] = 12 | |
fig = plt.figure(figsize=(15,20)) | |
for i in range(y[0].shape[0]): | |
axL = fig.add_subplot(row, col, 1+i*2) | |
axL.plot(data_range, y[0][i], linewidth=2) | |
if(i==0): axL.set_title(title[0], fontsize=18) | |
axL.set_xlabel(xlabel[0], fontsize=18) | |
axL.set_ylabel(ylabel[0][i], fontsize=18) | |
axL.grid(True) | |
axR = fig.add_subplot(row, col, 2+i*2) | |
axR.plot(data_range, y[1][i], linewidth=2) | |
if(i==0): axR.set_title(title[1], fontsize=18) | |
axR.set_xlabel(xlabel[1], fontsize=18) | |
axR.set_ylabel(ylabel[1][i], fontsize=18) | |
axR.grid(True) | |
for ax in fig.axes: | |
plt.sca(ax) | |
plt.xticks(rotation=30) | |
fig.show() | |
return fig |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import matplotlib.pyplot as plt | |
from mpl_toolkits.mplot3d import Axes3D | |
import matplotlib.animation as animation | |
import random | |
from mpl_toolkits.mplot3d import Axes3D | |
from scipy.interpolate import griddata | |
import pandas as pd | |
from keras import regularizers | |
import datetime | |
import random as rnd | |
from sklearn.metrics import r2_score | |
import math | |
from tqdm import tqdm | |
import copy | |
from sklearn.metrics import mean_squared_error | |
#Random Forest | |
from sklearn.ensemble import RandomForestRegressor | |
from sklearn import tree | |
import pydotplus as pdp | |
import pickle | |
from PIL import Image | |
from io import BytesIO | |
from sklearn.model_selection import train_test_split | |
from sklearn.model_selection import KFold | |
import warnings | |
warnings.filterwarnings("ignore") | |
if __name__ == '__main__': | |
rf = RF() | |
df = pd.read_csv('kyuri_liquid_202001-06.csv') # file name | |
df_ls, df_vs = rf.split(df=df, learning=0.8, fold=5) | |
#print(np.sort(df_ls[0].values[:,0])) | |
#print(np.sort(df_v.values[:,0])) | |
x_h_c = ["radiation" | |
, "temp" | |
, "day_temp" | |
, "night_temp" | |
, "day_satiety" | |
, "night_satiety"] # inputs (climate) | |
""" | |
# For net_photo | |
x_h_c = ["radiation" | |
, "night_temp" | |
, "temp" | |
, "day_temp"] | |
# For net_photo | |
x_h_c = ["radiation" | |
, "temp" | |
, "day_temp"] | |
""" | |
x_h = x_h_c | |
y_h = ["net_photo"] # outputs | |
for j in range(len(df_ls)): | |
df_l = df_ls[j] | |
df_v = df_vs[j] | |
print(df_l.values[:,0]) | |
x = rf.prepare(df_l, x_h) | |
# Training | |
forests = [] | |
for targ in y_h: | |
forest, indices, importances = rf.machineL(x, df_l[targ], targ, 0) # x, y | |
forests.append(forest) | |
#rf.showRF(forests[0]) | |
# Validation | |
#rf.validation(forests, df_v, x_h_c, y_h, j) | |
#rf.gradation(forests[0], [20.0, 25.0, -1, -2, 6.0, 2.0], np.arange(11)*4, np.arange(11)*4) | |
print("-----") | |
# ---High contributing | |
high_cont = False | |
if(high_cont): | |
hc_x_h = [] | |
for i, hc in enumerate(indices): | |
hc_x_h.append(x_h_c[hc]) | |
x = rf.prepare(df_l, hc_x_h) | |
forests = [] | |
for targ in y_h: | |
forest, indices, importances = rf.machineL(x, df_l[targ], targ, j) # x, y | |
forest = pickle.load(open(targ+str(j)+'.sav', 'rb')) | |
forests.append(forest) | |
print("-") | |
#print(rf.validation(forests, df_v, hc_x_h, y_h, j)) | |
print("-----") | |
""" | |
genes = [Gene(6, [5,20,28,14,5,1],[20,30,33,26,10,4]) for i in range(10000)] | |
for i in range(100): | |
[g.mutation() for g in genes] | |
genes = Gene.sortGene(genes, forests[0]) | |
print(i, genes[0].gene, genes[0].fitness) | |
genes = Gene.select(genes) | |
genes = Gene.crossover(genes) | |
""" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class RF: | |
def split(self, df, learning=0.8, fold=5): | |
#l = int(df.shape[0]*learning) | |
#df_l, df_v = train_test_split(df, train_size=learning) | |
#df_l, df_v = df[:l], df[l:] | |
kf = KFold(n_splits=fold, shuffle=False, random_state=0) | |
df_l, df_v = [], [] | |
for i, (train_index, test_index) in enumerate(kf.split(df)): | |
df_l.append([]), df_v.append([]) | |
df_l[i]=df.iloc[train_index] | |
df_v[i]=df.iloc[test_index] | |
return df_l, df_v | |
def prepare(self, df, header): | |
integrated = np.stack([df[h] for h in header]) | |
integrated = integrated.T | |
return integrated | |
def machineL(self, x, y, target, j): | |
#モデル | |
forest = RandomForestRegressor(n_estimators=1000, n_jobs = -1) | |
f = forest.fit(x, y) | |
pickle.dump(forest, open('./'+target+str(j)+'.sav','wb')) | |
#print("score:", f.score(t_x, t_y)) | |
importances = forest.feature_importances_ | |
indices = np.argsort(importances)[::-1] | |
for f in range(x.shape[1]): | |
print("%d. feature %d (%f)" % (f+1, indices[f], importances[indices[f]])) | |
return forest, indices, importances | |
def validation(self, forests, df, x_h_c, y_h, j): | |
#評価 | |
l = str(len(x_h_c)) | |
x_c = rf.prepare(df, x_h_c) # climate data | |
y = rf.prepare(df, y_h) # Actual data | |
hist_p = [] | |
hist_y = [] | |
i = 0 | |
for eachx_c in x_c: | |
x = eachx_c | |
predicted_p = np.empty(0) | |
for forest in forests: | |
forsee = forest.predict(x.reshape(1,-1)) | |
if(abs(forsee) < 0.0001): | |
forsee = 0 | |
predicted_p = np.append(predicted_p, forsee) | |
#x_p += predicted_x # integrated | |
#y_ += y[i] # integrated | |
x_p = predicted_p | |
y_ = y[i] | |
i += 1 | |
hist_p.append(copy.copy(x_p)) | |
hist_y.append(copy.copy(y_)) | |
#print(i, x_p) | |
#hist_x = [l.tolist() for l in hist_x] | |
#print(hist_x[0]) | |
#showRF(forests[id]) | |
p = np.array(hist_p) | |
y = np.array(hist_y) | |
joint = np.concatenate([y, p], axis=1) | |
df = pd.DataFrame(joint, columns = np.append([h+"(actual)" for h in y_h], [h+"(predicted)" for h in y_h])) | |
df.to_csv("result"+l+"_"+str(j)+".csv") | |
g = Graphics() | |
fig = g.dayPlot2D("20191231", y=[y.T, p.T], title=["Actual", "Predicted"], xlabel=["day","day"], ylabel=[y_h, y_h]) | |
fig.savefig("Predicted"+l+"_"+str(j)+".png") | |
return mean_squared_error(y.T[0], p.T[0]) | |
""" | |
plt.scatter(delY, predicted, alpha=0.3) | |
plt.xlabel("TOMGRO") | |
plt.ylabel("Predicted") | |
plt.show() | |
""" | |
#相関係数 | |
#return np.dot(predicted, delY)/(np.linalg.norm(predicted, ord=2)*np.linalg.norm(delY, ord=2)) | |
return 0 | |
def gradation(self, forest, fix, range1, range2): | |
hist_p = np.empty(0) | |
for i, x1 in enumerate(range1): | |
forsee_r = np.empty(0) | |
for j, x2 in enumerate(range2): | |
x = np.array(copy.copy(fix)) | |
x = np.where(x==-1, x1, x) | |
x = np.where(x==-2, x2, x) | |
forsee = forest.predict(x.reshape(1,-1)) | |
print(i, j, x, forsee) | |
forsee_r = np.append(forsee_r, copy.copy(forsee)) | |
forsee_r = np.insert(forsee_r, 0, range1[i]) | |
hist_p = np.append(hist_p, copy.copy(forsee_r)) | |
hist_p = np.insert(hist_p, 0, range2) | |
hist_p = np.insert(hist_p, 0, 0) | |
hist_p = hist_p.reshape(-1, len(range2)+1) | |
df = pd.DataFrame(hist_p) | |
df.to_csv("gradation.csv") | |
def showRF(self, rf): | |
estimator = rf.estimators_[0] | |
filename = "./tree.png" | |
dot_data = tree.export_graphviz( | |
estimator, | |
out_file=None, | |
filled=True, | |
rounded=True, | |
special_characters=True | |
) | |
graph = pdp.graph_from_dot_data(dot_data) | |
graph.write_png(filename) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment