import pyVIA.core as via
# ensure the data and label files are in csv format when you download/save them
#multifurcation
#the root is automatically set to  root_user = 'M1'
via.main_Toy(ncomps=10, knn=30,dataset='Toy3', random_seed=2,foldername = ".../Trajectory/Datasets/") #multifurcation
#disconnected trajectory
# The root is automatically set as a list root_user = ['T1_M1', 'T2_M1'] # e.g. T2_M3 is a cell belonging to the 3rd Milestone (M3) of the second Trajectory (T2)
via.main_Toy(ncomps=10, knn=30,dataset='Toy4',random_seed=2,foldername =".../Trajectory/Datasets/") #2 disconnected trajectories

#when running from an IDE you need to call the function in the following way to ensure the parallel processing works:
import os
import pyVIA.core as via
f= os.path.join(r'C:\Users\...\Documents'+'\\')
def main():
    via.main_Toy(ncomps=10, knn=30,dataset='Toy3', random_seed=2,foldername= f)    
if __name__ =='__main__':
    main()
    
#when running directly from terminal:
import os
import pyVIA.core as via
f= os.path.join(r'C:\Users\...\Documents'+'\\')
via.main_Toy(ncomps=10, knn=30,dataset='Toy3', random_seed=2,foldername= f)    

#runtime on single core, 8GB RAM 64bit Windows is about 8-10 minutes. This can be lowered by reducing the number of MCMC simulations (num_mcmc_simulations).
import pyVIA.core as via
#Windows example path for folder where EBdata.mat is saved: f= os.path.join(r'C:\Users\...\Documents'+'\\')
via.main_EB_clean(ncomps=30, knn=20, v0_random_seed=24, foldername = f) # Most reasonable parameters of ncomps (10-200) and knn (15-50) work well

# Read the two files:
# 1) The first file contains 200PCs of the Bcell filtered and normalized data for the first 5000 HVG.
# 2) The second file contains raw count data for marker genes

data = pd.read_csv('./Bcell_200PCs.csv')
data_genes = pd.read_csv('./Bcell_markergenes.csv')
data_genes = data_genes.drop(['cell'], axis=1)
true_label = data['time_hour']
data = data.drop(['cell', 'time_hour'], axis=1)
adata = sc.AnnData(data_genes)
adata.obsm['X_pca'] = data.values

# use UMAP or PHate to obtain embedding that is used for single-cell level visualization
embedding = umap.UMAP(random_state=42, n_neighbors=15, init='random').fit_transform(data.values[:, 0:5])

# list marker genes or genes of interest if known in advance. otherwise marker_genes = []
marker_genes = ['Igll1', 'Myc', 'Slc7a5', 'Ldha', 'Foxo1', 'Lig4', 'Sp7']  # irf4 down-up
# call VIA. We identify an early (suitable) start cell root = [42]. Can also set an arbitrary value
via.via_wrapper(adata, true_label, embedding, knn=10, ncomps=20, jac_std_global=0.15, root=[42], dataset='',
            random_seed=1,v0_toobig=0.3, v1_toobig=0.1, marker_genes=marker_genes)

import scanpy as sc
import pandas as pd

#foldername corresponds to the location where you have saved the Toy Disconnected data (shown in example 2)
#Read in the data and labels
df_counts = pd.read_csv(foldername + "toy_disconnected_M9_n1000d1000.csv", 'rt', delimiter=",")
df_ids = pd.read_csv(foldername + "toy_disconnected_M9_n1000d1000_ids.csv", 'rt', delimiter=",")

# Make AnnData object for wrapper function to read-in data and do PCA
df_ids['cell_id_num'] = [int(s[1::]) for s in df_ids['cell_id']]
df_counts = df_counts.drop('Unnamed: 0', 1)
df_ids = df_ids.sort_values(by=['cell_id_num'])
df_ids = df_ids.reset_index(drop=True)
true_label = df_ids['group_id']
adata_counts = sc.AnnData(df_counts, obs=df_ids)
sc.tl.pca(adata_counts, svd_solver='arpack', n_comps=10)

#Since there are 2 disconnected trajectories, we provide 2 arbitrary roots (start cells).If there are more disconnected paths, then VIA arbitrarily selects roots. #The root can also just be arbitrarily set as [1] and VIA can detect how many additional roots it must add
# The root can also be provided as a cell type level label corresponding to the groups present in "true_label", in this case the dataset must be set to 'group'
via.via_wrapper_disconnected(adata_counts, true_label, embedding=adata_counts.obsm['X_pca'][:, 0:2], root=[1,1], preserve_disconnected=True, knn=30, ncomps=10,cluster_graph_pruning_std = 1)

#in the case of connected data (i.e. only 1 graph component. e.g. Toy Data Multifurcating) then the wrapper function from example 3.a can be used:
via.via_wrapper(adata_counts, true_label, embedding=  adata_counts.obsm['X_pca'][:,0:2], root=[1], knn=30, ncomps=10,cluster_graph_pruning_std = 1)

conda create --name ViaEnv python=3.7 
pip install pyVIA // tested on linux Ubuntu 16.04 and Windows 10

pip install pybind11
pip install hnswlib
pip install pyVIA

git clone https://github.com/ShobiStassen/VIA.git 
python3 setup.py install // cd into the directory of the cloned VIA folder containing setup.py and issue this command

conda create --name ViaEnv python=3.7 
pip install pybind11
conda install -c conda-forge hnswlib
pip install pyVIA

pip install pybind11, hnswlib, igraph, leidenalg>=0.7.0, umap-learn, numpy>=1.17, scipy, pandas>=0.25, sklearn, termcolor, pygam, phate, matplotlib,scanpy
pip install pyVIA