# 'RH',
# 'wind',
# 'rain'
]
# data.drop(labels= labels,axis= 1,inplace =True)
err = []
err1 = []
err2 = []
err3 = []
err4 = []
out = []
for i in range(75, 100, 1):
out.append(float(i) / 100)
d = remove_outlier_h(data, 'area', float(i) / 100)
y = d.area
plt.show()
y = d.area
x = d.drop(labels=['area'], axis=1)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
random_state=10,
test_size=0.3)
reg = SVR(kernel='rbf',
degree=1,
gamma='auto',
coef0=0.0,
tol=0.001,
C=1.0,
# 'X',
# 'Y',
# 'month',
# 'day',
# 'FFMC',
# 'DMC',
# 'DC',
# 'ISI',
# 'temp',
# 'RH',
# 'wind',
# 'rain'
]
data.drop(labels=labels, axis=1, inplace=True)
d = remove_outlier_h(data, 'area', 0.85)
y = d.area
x = d.drop(labels=['area'], axis=1)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
random_state=10,
test_size=0.3)
err = []
err1 = []
err2 = []
err3 = []
err4 = []
out = []
for i in range(1, 100):
import pandas as pd
import matplotlib.pyplot as plt
import functions as fnc
import math
data = pd.read_csv("../forestfires.csv")
# data = data.drop(labels=['day'],axis=1)
data.month.replace(('jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug',
'sep', 'oct', 'nov', 'dec'),
(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12),
inplace=True)
data.day.replace(('mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun'),
(1, 2, 3, 4, 5, 6, 7),
inplace=True)
d = fnc.remove_outlier_h(data, 'area', 0.9)
y = d.area
plt.title("Burned area in ha")
plt.ylabel("Frequency")
plt.hist(y)
y = list(y)
print(len(y))
plt.show()
