for sheet in data_sheets:
row = sheet.nrows # 行数
col = sheet.ncols # 列数
for j in range(1, row):
labels.append(sheet_names[i])
data.append(sheet.row_values(j)[1:5])
i += 1
data = np.array(data)
return data, [i[-2] for i in labels]
sleep_data, sleep_labels = read_data_by_sheets('data/sleep.xlsx')
# PCA
dim_data, ratio, result = get_pca(sleep_data, c=2, with_normalize=False)
# print(ratio)
# 绘图13
x = [i[0] for i in dim_data]
y = [i[1] for i in dim_data]
default_colors = ['r', 'b', 'g', 'c', 'm']
colors = get_color(sleep_labels, default_colors)
print('Drawing...')
draw_scatter(x, y, sleep_labels, colors)
default_colors = [[0, 0.8, 1], [0, 0.5, 0.5], [0.2, 0.8, 0.8], [0.2, 0.4, 1], [0.6, 0.8, 1], [1, 0.6, 0.8],
[0.8, 0.6, 1], [1, 0.8, 0.6], [1, 0, 0], [0, 1, 0]]
for j in range(1, 10):
acc_arr = []
# 文件路径 filePath = 'data/41592_2017_BFnmeth4179_MOESM235_ESM.xlsx' x1 = xlrd.open_workbook(filePath) sheet = x1.sheets() labels = sheet[0].col_values(3)[1:] # joblib.dump(X, 'datasets/human_islets.pkl') # joblib.dump(labels, 'datasets/human_islets_labels.pkl') print(labels) print(X.shape) print(datetime.datetime.now()) # PCA dim_data, ratio, result = get_pca(X, c=11, with_normalize=False) print(sum(ratio)) # t-SNE dim_data = t_SNE(dim_data, perp=5, with_normalize=False) # get two coordinates x = [i[0] for i in dim_data] y = [i[1] for i in dim_data] # get color list based on labels default_colors = ['b', 'g', 'r', 'm', 'y', 'k'] colors = get_color(labels, default_colors) # plot draw_scatter(x, y, labels, colors)
import numpy as np
import joblib
# read labels
labels = read_from_txt('data/human_islets_labels.txt')
labels = [i[-1] for i in labels][1:]
print(len(labels))
# read data
X = read_from_txt('data/human_islets.txt')
X = X.T[1:, 1:].astype(np.float64)
print(X.shape)
# joblib.dump(X, 'datasets/human_islets.pkl')
# joblib.dump(labels, 'datasets/human_islets_labels.pkl')
# dimenison reduction
# t-SNE
# dim_data = t_SNE(X, perp=5, with_normalize=True)
# PCA
dim_data, ratio, result = get_pca(X, c=2, with_normalize=True)
# get two coordinates
x = [i[0] for i in dim_data]
y = [i[1] for i in dim_data]
# get color list based on labels
colors = get_color(labels)
# plot
draw_scatter(x, y, labels, colors)
genes_P = []
idx = 0
for gene in GEM:
gene = np.array(gene)
if len(gene[gene > 0]) >= 10:
GEM_P.append(gene)
genes_P.append(genes[idx])
idx += 1
GEM_P = np.array(GEM_P)
print(GEM_P.shape)
print(len(genes_P))
# In[ ]:
dim_data, ratio, result = get_pca(GEM_P.T, c=20, with_normalize=True)
dim_data = t_SNE(dim_data, perp=30, with_normalize=True)
x = [i[0] for i in dim_data]
y = [i[1] for i in dim_data]
default_colors = ['c', 'b', 'g', 'r', 'm', 'y', 'k']
colors = get_color(labels, default_colors)
draw_scatter(x, y, labels, colors)
# In[4]:
print(genes_P.index('POU5F1'))
print(genes_P.index('GATA6'))
# In[ ]:
# Scatter of gene GATA6 and POU5F1