aifh_dir = os.path.abspath(aifh_dir + os.sep + ".." + os.sep + "lib" + os.sep + "aifh")
sys.path.append(aifh_dir)
from normalize import Normalize
# find the Wisconsin breast cancer data set
dataFile = os.path.dirname(os.path.realpath(__file__))
dataFile = os.path.abspath(dataFile + "../../datasets/breast-cancer-wisconsin.csv")
# Normalize the Wisconsin file.
norm = Normalize()
data_file_work = norm.load_csv(dataFile)
norm.delete_unknowns(data_file_work)
norm.col_delete(data_file_work, 0)
norm.col_replace(data_file_work, 9, 4, 1, 0)
for i in xrange(0, 9):
norm.make_col_numeric(data_file_work, i)
df = pd.DataFrame(data_file_work)
df.columns = ["clump_thickness", "size_uniformity", "shape_uniformity", "marginal_adhesion", "epithelial_size",
"bare_nucleoli", "bland_chromatin", "normal_nucleoli", "mitoses", "class"]
train_cols = df.columns[0:9]
# Perform the logistic regression.
logit = sm.Logit(df['class'], df[train_cols])
# fit the model
aifh_dir = os.path.abspath(aifh_dir + os.sep + ".." + os.sep + "lib" + os.sep + "aifh")
sys.path.append(aifh_dir)
from normalize import Normalize
k = 3
# find the Iris data set
irisFile = os.path.dirname(os.path.realpath(__file__))
irisFile = os.path.abspath(irisFile + "../../datasets/iris.csv")
# Read the Iris data set.
print('Reading CSV file: ' + irisFile)
norm = Normalize()
iris_data = norm.load_csv(irisFile)
# Prepare the iris data set.
classes = norm.col_extract(iris_data, 4)
norm.col_delete(iris_data, 4)
for i in range(0, 4):
norm.make_col_numeric(iris_data, i)
# Cluster the Iris data set.
res, idx = kmeans2(np.array(iris_data), k)
for cluster_num in range(0, k):
print( "Cluster #" + str(cluster_num + 1))
for i in range(0, len(idx)):
if idx[i] == cluster_num:
print( str(iris_data[i]) + "," + classes[i])
"aifh")
sys.path.append(aifh_dir)
from normalize import Normalize
k = 3
# find the Iris data set
irisFile = os.path.dirname(os.path.realpath(__file__))
irisFile = os.path.abspath(irisFile + "../../datasets/iris.csv")
# Read the Iris data set.
print('Reading CSV file: ' + irisFile)
norm = Normalize()
iris_data = norm.load_csv(irisFile)
# Prepare the iris data set.
classes = norm.col_extract(iris_data, 4)
norm.col_delete(iris_data, 4)
for i in range(0, 4):
norm.make_col_numeric(iris_data, i)
# Cluster the Iris data set.
res, idx = kmeans2(np.array(iris_data), k)
for cluster_num in range(0, k):
print("Cluster #" + str(cluster_num + 1))
for i in range(0, len(idx)):
if idx[i] == cluster_num:
print(str(iris_data[i]) + "," + classes[i])
"aifh")
sys.path.append(aifh_dir)
from normalize import Normalize
# find the Wisconsin breast cancer data set
dataFile = os.path.dirname(os.path.realpath(__file__))
dataFile = os.path.abspath(dataFile +
"../../datasets/breast-cancer-wisconsin.csv")
# Normalize the Wisconsin file.
norm = Normalize()
data_file_work = norm.load_csv(dataFile)
norm.delete_unknowns(data_file_work)
norm.col_delete(data_file_work, 0)
norm.col_replace(data_file_work, 9, 4, 1, 0)
for i in range(0, 9):
norm.make_col_numeric(data_file_work, i)
df = pd.DataFrame(data_file_work)
df.columns = [
"clump_thickness", "size_uniformity", "shape_uniformity",
"marginal_adhesion", "epithelial_size", "bare_nucleoli", "bland_chromatin",
"normal_nucleoli", "mitoses", "class"
]
train_cols = df.columns[0:9]
# Perform the logistic regression.