# Defines Logistic Regression Model:
model = LogisticRegression()
# Trains the model
model.fit(XTrain, yTrain)
yPredicted = model.predict(XTest)
print("Die Vorhersagegenauigkeit entspricht: ")
print(100 * model.score(XTest, yTest), "%")
# Prints diagram of the real test Data:
plt.scatter(XTest[:, 0], XTest[:, 1], c=yTest)
plt.xlabel("Number of Sport activities per month")
plt.ylabel("Number of eating healthy per month")
plt.title("REAL TEST DATA")
plt.show()
# Prints diagram of the Prediction:
plt.scatter(XTest[:, 0], XTest[:, 1], c=yPredicted)
plt.xlabel("Number of Sport activities per month")
plt.ylabel("Number of eating healthy per month")
plt.title("PREDICTED DATA")
plt.show()
# Prints diagramm of the real test Data with seperator
plot_classifier(model,
XTest,
yTest,
proba=True,
xlabel="Number of Sport activities per month",
ylabel="Number of eating healthy per month")
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=0,
test_size=0.25)
scaler = StandardScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)
model = SVC(kernel="poly", degree=2, coef0=1, C=1)
model.fit(X_train, y_train)
print(model.score(X_test, y_test))
# Trainings-Daten plotten
plot_classifier(model,
X_train,
y_train,
proba=False,
xlabel="Alter",
ylabel="Interesse")
# Testdaten plotten
plot_classifier(model,
X_test,
y_test,
proba=False,
xlabel="Alter",
ylabel="Interesse")
import pandas as pd
import graphviz
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from helper import plot_classifier
df = pd.read_csv("classification.csv")
y = df["success"].values
X = df[["age", "interest"]].values
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=0,
test_size=0.25)
model = RandomForestClassifier(criterion="entropy",
n_estimators=100) # Anzahl der Bäume im Wald
model.fit(X_train, y_train)
plot_classifier(model,
X_train,
y_train,
proba=True,
xlabel="Alter",
ylabel="Interesse")
print(model.score(X_test, y_test))
random_state=0,
test_size=0.4)
from sklearn.neighbors import KNeighborsClassifier
model = KNeighborsClassifier()
model.fit(X_train, y_train)
print(model.score(X_test, y_test))
from helper import plot_classifier
# train data plot
plot_classifier(model,
X_train,
y_train,
proba=False,
xlabel="feature",
ylabel="label")
# test data plot
plot_classifier(model,
X_test,
y_test,
proba=False,
xlabel="feature",
ylabel="label")
#Task 4 varitity of classifiers
###############################################################################
import os
os.chdir("./")
Y = DF["desease"].values
# Splitting the Set in Train and Test Data:
XTRAIN, XTEST, YTRAIN, YTEST = train_test_split(X,
Y,
random_state=0,
test_size=0.25)
# creates a random forest with a maximum node-depth of 4
# and a minumum number of 3 examples per leaf
MODEL = RandomForestClassifier(criterion="gini",
max_depth=4,
min_samples_leaf=3)
MODEL = MODEL.fit(XTEST, YTEST)
print(MODEL.score(XTEST, YTEST))
plot_classifier(MODEL,
XTRAIN,
YTRAIN,
proba=True,
xlabel="monthlySport",
ylabel="monthlyHealthyFood")
plot_classifier(MODEL,
XTEST,
YTEST,
proba=True,
xlabel="monthlySport",
ylabel="monthlyHealthyFood")