wstępne drzewko

This commit is contained in:
xkamikoo 2020-05-15 13:54:18 +02:00
parent 677cd02e6f
commit 893793c0bf

200
Kamila.py
View File

@ -1,9 +1,203 @@
class main():
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn import metrics
import numpy
header = ["ready", "hydration", "weeds", "planted"]
def check(field):
if field == 0:
return [0, 0, 0, 'N']
elif field == 1:
return [0, 0, 1, 'N']
elif field == 2:
return [0, 0, 0, 'Y']
elif field == 3:
return [0, 0, 1, 'Y']
elif field == 4:
return [0, 1, 0, 'N']
elif field == 5:
return [0, 1, 1, 'N']
elif field == 6:
return [0, 1, 0, 'Y']
elif field == 7:
return [0, 1, 1, 'Y']
elif field == 8:
return [1, 0, 0, 'N']
else:
print("wrong field number")
def un_values(rows, col):
return set([row[col] for row in rows])
def class_counts(rows):
counts = {}
for row in rows:
label = row[-1]
if label not in counts:
counts[label] = 0
counts[label] += 1
return counts
def is_numeric(value):
return isinstance(value, int) or isinstance(value, float)
class Question():
def __init__(self, column, value):
self.column = column
self.value = value
def match(self, example):
val = example[self.column]
if is_numeric(val):
return val == self.value
else:
return val != self.value
def __repr__(self):
condition = "!="
if is_numeric(self.value):
condition = "=="
return "Is %s %s %s?" %(
header[self.column], condition, str(self.value)
)
def partition(rows, question):
true_rows, false_rows = [], []
for row in rows:
if question.match(row):
true_rows.append(row)
else:
false_rows.append(row)
return true_rows, false_rows
def gini(rows):
counts = class_counts(rows)
impurity = 1
for lbl in counts:
prob_of_lbl = counts[lbl]/float(len(rows))
impurity -= prob_of_lbl**2
return impurity
def info_gain(left, right, current_uncertainty):
p = float(len(left))/(len(left) + len(right))
return current_uncertainty - p*gini(left) - (1-p) * gini(right)
def find_best_split(rows):
best_gain = 0
best_question = None
current_uncertainty = gini(rows)
n_features = len(rows[0]) - 1
for col in range(n_features):
values = set([row[col] for row in rows])
for val in values:
question = Question(col, val)
true_rows, false_rows = partition(rows, question)
if len(true_rows) == 0 or len(false_rows) == 0:
continue
gain = info_gain(true_rows,false_rows,current_uncertainty)
if gain >= best_gain:
best_gain, best_question = gain, question
return best_gain, best_question
class Leaf:
def __init__(self, rows):
self.predictions = class_counts(rows)
class DecisionNode:
def __init__(self, question, true_branch, false_branch):
self.question = question
self.true_branch = true_branch
self.false_branch = false_branch
def build_tree(rows):
gain, question = find_best_split(rows)
if gain == 0:
return Leaf(rows)
true_rows, false_rows = partition(rows, question)
true_branch = build_tree(true_rows)
false_branch = build_tree(false_rows)
return DecisionNode(question, true_branch, false_branch)
def print_tree(node, spacing=""):
if isinstance(node, Leaf):
print(spacing + "Predict", node.predictions)
return
print(spacing + str(node.question))
print(spacing + '--> True: ')
print_tree(node.true_branch, spacing + " ")
print(spacing + '--> False: ')
print_tree(node.false_branch, spacing + " ")
def classify(row, node):
if isinstance(node, Leaf):
return node.predictions
if node.question.match(row):
return classify(row, node.true_branch)
else:
return classify(row,node.false_branch)
def print_leaf(counts):
total = sum(counts.values()) * 1.0
probs = {}
for lbl in counts.keys():
probs[lbl] = str(int(counts[lbl]/total * 100)) + "%"
return probs
class Main():
def __init__(self,traktor,field,ui,path):
self.traktor = traktor
self.field = field
self.ui = ui
self.path = path
def main(self):
pass
def tree(field):
array = ([[8, 8, 8, 8, 8, 8, 8, 8, 8, 8],
[7, 7, 7, 7, 7, 7, 7, 7, 7, 7],
[6, 6, 6, 6, 6, 6, 6, 6, 6, 6],
[5, 5, 5, 5, 5, 5, 5, 5, 5, 5],
[4, 4, 4, 4, 4, 4, 4, 4, 4, 4],
[3, 3, 3, 3, 3, 3, 3, 3, 3, 3],
[2, 2, 2, 2, 2, 2, 2, 2, 2, 2],
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])
testing_data = []
for i in range(10):
verse = field[i]
for j in verse:
coord = (i, j)
current_field = check(verse[j])
testing_data.append(current_field)
x = build_tree(testing_data)
print_tree(x)