Clustering analysis

import pandas as pd
from sklearn.cluster import AgglomerativeClustering as AC
import numpy as np
import matplotlib.pyplot as plt
import scipy.cluster.hierarchy as hc
from scipy.spatial.distance import pdist,squareform
from scipy.cluster.hierarchy import ward,fcluster,is_valid_linkage

# read data
data = pd.read_csv("/home/jovyan/PEP_Lev1/Score.csv", sep = ',',usecols = range(0,4))
data["Jaccard_Distance"] = 1- data["Jaccard_score"]
data["Weighted_Jacc_Dist"] =  1-data["Weighed_score"]

#redefining column names
data.columns = ["Gene_symbols", "Jaccard_Similarity","Weighted_Similarity","Chebi_Compounds","Jaccard_Distance","Weighted_Jacc_Dist"]

#SUBSET DATA
data_sub = data[["Gene_symbols","Chebi_Compounds","Jaccard_Distance"]].copy()  
symbols = data[["Gene_symbols"]].values.tolist()
data_matrix = data_sub.pivot_table(index=['Gene_symbols'],values = ['Jaccard_Distance'],columns=['Chebi_Compounds'],aggfunc=np.mean,fill_value=0)

#Hierarchical clustering 
T= hc.linkage(test, method = 'ward')
fig = plt.figure(figsize=(20, 10))
plt.title('Hierarchical Clustering Dendrogram')
plt.xlabel('Gene_symbol')
plt.ylabel('distance')
hc.dendrogram(
    T,
    leaf_rotation=90.,  # rotates the x axis labels
    leaf_font_size=9,  # font size for the x axis labels
    p=5,
    truncate_mode='level',
    labels = test.index,
    orientation='top'
)
plt.show()
hc.leaves_list(T)[0:119]
lev1genes = [symbls[x] for x in hc.leaves_list(T)[0:119]] # to validate and trace back

#Heat map with Dendogram