RF_For_Lettuce

graphic.py

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

main.py

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

#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

import warnings
warnings.filterwarnings("ignore")
   
if __name__ == '__main__':
  rf = RF()
  
  # CHANGE !!
  df_l = pd.read_csv('training.csv') # file name (Learning)
  df_v = pd.read_csv('validation.csv') # file name (Validation)
  x_h_c = ["Light", "CO2", "Temp"] # inputs (climate)
  x_h_p = ["AofF", "AofL", "AofLA"] # inputs (plants)
  x_h = np.append(x_h_p, x_h_c) # inputs
  y_h = ["dF", "dL", "dLA"] # outputs
  # ######
  
  x = rf.prepare(df_l, x_h)
  print(x)
  
  # Training
  forests = []
  for targ in y_h:
    forest = rf.machineL(x, df_l[targ], targ) # x, y
    forests.append(forest)
    print("-----")
    
  rf.showRF(forests[0])
  
  # Validation
  rf.validation(forests, df_v, x_h_c, x_h_p, y_h)
  rf.predict(forests, df_v, x_h_c, x_h_p)

rf.py

class RF:
  def split(self, df, learning=0.8, fold=5):
    l = int(df.shape[0]*learning)
    df_l, df_v = df[:l], df[l:]
    return df_l, df_v 
  
  def prepare(self, df, header):
    integrated = np.stack([df[h] for h in header])
    return integrated.T
  
  def machineL(self, x, y, target):
    #モデル
    forest = RandomForestRegressor(n_estimators=100, n_jobs = -1)
    f = forest.fit(x, y)
    pickle.dump(forest, open('./'+target+'.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
  
  def validation(self, forests, df, x_h_c, x_h_p, y_h):
    #評価
    x_c = rf.prepare(df, x_h_c) # climate data
    x_p = rf.prepare(df, x_h_p)[0] # plants growing initial data
    y = rf.prepare(df, y_h) # Actual data
    print("y", y)
    y_ = copy.copy(x_p)
    hist_x = []
    hist_y = []

    i = 0
    for eachx_c in x_c:
      hist_x.append(copy.copy(x_p))
      hist_y.append(copy.copy(y_))
      x = np.append(x_p, eachx_c)
      predicted_x = np.empty(0)
      for forest in forests:
        forsee = forest.predict(x.reshape(1,-1))
        if(abs(forsee) < 0.0001):
          forsee = 0
        predicted_x = np.append(predicted_x, forsee)
      x_p += predicted_x
      y_ += y[i]
      i += 1
      #print(i, x_p)

    #hist_x = [l.tolist() for l in hist_x]
    #print(hist_x[0])
    #showRF(forests[id])
    p = np.array(hist_x)
    y = np.array(hist_y)

    joint = np.concatenate([y, p], axis=1)
    df = pd.DataFrame(joint, columns = np.append(x_h_p, x_h_p))
    df.to_csv("result.csv")
    
    g = Graphics()
    fig = g.dayPlot2D("20200629", y=[y.T, p.T], title=["Actual", "Predicted"], xlabel=["day","day"], ylabel=[x_h_p,x_h_p])
    fig.savefig("Predicted.png")
      #outTxt(y[id], "testy2_"+str(id))

    #outTxt(hist_x, "testx2")

    """
    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 predict(self, forests, df, x_h_c, x_h_p):
    #評価
    x_c = rf.prepare(df, x_h_c) # climate data
    x_p = rf.prepare(df, x_h_p)[0] # plants growing initial data
    hist_x = []

    i = 0
    for eachx_c in x_c:
      hist_x.append(copy.copy(x_p))
      x = np.append(x_p, eachx_c)
      predicted_x = np.empty(0)
      for forest in forests:
        forsee = forest.predict(x.reshape(1,-1))
        if(abs(forsee) < 0.0001):
          forsee = 0
        predicted_x = np.append(predicted_x, forsee)
      x_p += predicted_x
      i += 1
      
    p = np.array(hist_x)
    
    df = pd.DataFrame(p, columns = x_h_p)
    df.to_csv("predicted.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)
    
def removeNan(x):
  #...
  return res_x