data = pd.read_csv("tree_addhealth.csv")

#upper-case all colu`enter code here`mn names in DataFrame
data.columns = map(str.upper, data.columns)

data_clean = data.dropna()

cluster=data_clean[['ALCEVR1','MAREVER1','ALCPROBS1','DEVIANT1','VIOL1',
'DEP1','ESTEEM1','SCHCONN1','PARACTV', 'PARPRES','FAMCONCT']]

clustervar=cluster.copy()
clustervar['ALCEVR1']=preprocessing.scale(clustervar['ALCEVR1'].astype('float64'))
clustervar['ALCPROBS1']=preprocessing.scale(clustervar['ALCPROBS1'].astype('float64'))
clustervar['MAREVER1']=preprocessing.scale(clustervar['MAREVER1'].astype('float64'))
clustervar['DEP1']=preprocessing.scale(clustervar['DEP1'].astype('float64'))
clustervar['ESTEEM1']=preprocessing.scale(clustervar['ESTEEM1'].astype('float64'))
clustervar['VIOL1']=preprocessing.scale(clustervar['VIOL1'].astype('float64'))
clustervar['DEVIANT1']=preprocessing.scale(clustervar['DEVIANT1'].astype('float64'))
clustervar['FAMCONCT']=preprocessing.scale(clustervar['FAMCONCT'].astype('float64'))
clustervar['SCHCONN1']=preprocessing.scale(clustervar['SCHCONN1'].astype('float64'))
clustervar['PARACTV']=preprocessing.scale(clustervar['PARACTV'].astype('float64'))
clustervar['PARPRES']=preprocessing.scale(clustervar['PARPRES'].astype('float64'))

clus_train, clus_test = train_test_split(clustervar, test_size=.3, random_state=123)

model3=KMeans(n_clusters=3)
model3.fit(clus_train)
clusassign=model3.predict(clus_train)
#clusassign.shape=(clus_train.shape[0],1)

y=Series(clusassign)
x=clus_train
target_names=[0,1,2]
colors = ['navy', 'turquoise', 'darkorange']

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
LDA_2 = LDA(n_components=2)
plot_columns = LDA_2.fit(x,y).transform(x)
for color, target_name in zip(colors, target_names):
plt.scatter(plot_columns[y == target_name, 0], plot_columns[y ==target_name, 1], alpha=.8, color=color,
label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('LDA of dataset')