#!/usr/bin/env python
# coding: utf-8

# In[1]:


get_ipython().system('pip install anndata')


# In[2]:


get_ipython().system('pip install scanpy')


# In[3]:


import scanpy as sc
import anndata
import importlib
from sklearn.decomposition import PCA

import matplotlib as mpl


# In[4]:


import h5py
import anndata

# Read the data into an AnnData object
adata = anndata.read_h5ad('C:/Users/smattaparthi/CS-297/TabulaSapiens_Heart_Dataset.h5ad')

print(adata) 


# In[5]:


#shape of data matrix
print(adata.shape)


# In[6]:


# Get the dimensions of the data 
print("Number of Cells:", adata.n_obs)
print("Number of Genes:", adata.n_vars)


# In[7]:


#view variable names(genes)
print(adata.var_names)


# In[8]:


#view observation names(cell)
print(adata.obs_names)


# In[11]:


#Preprocessing

#removing cells with less than 200 genes
sc.pp.filter_cells(adata, min_genes=200)

#removing genes with less than 3 cells
sc.pp.filter_genes(adata, min_cells=3)

print(adata)


# In[12]:


#Check the different cell types present in Heart Data

cell_type = adata.obs['cell_type']

print(cell_type)


# In[ ]:





# # Binary Classification on 'Cardiac Muscle Cell' 

# In[ ]:





# ## Logistic Regression 

# In[17]:


from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

# Identify Cardiac Muscle Cells from the dataset
cardiac_muscle_cells = adata.obs['cell_type'] == 'cardiac muscle cell'

# Create a Binary label for cardic muscle cells
adata.obs['is_cardiac_muscle'] = cardiac_muscle_cells.astype(int)

# Extract features (gene expressions) and Label to X and y variables respectively
X = adata.X
y = adata.obs['is_cardiac_muscle']

# Spliting data into train and test sets with train_test_split, # training data: 80%, testing data: 20% 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

#Instantiate logistic regression model
LR_Model = LogisticRegression(max_iter=1000)

#Train the model
LR_Model.fit(X_train, y_train)

# Predict Cardiac muscle cells test data
y_pred = LR_Model.predict(X_test)

print("\n\n Predicted target: 'cardiac muscle cell: '\n\n", y_pred)


# In[18]:


# Evaluate Logistic Regression Model performance
accuracy = accuracy_score(y_test, y_pred)
CM = confusion_matrix(y_test, y_pred)
CR = classification_report(y_test, y_pred)

print("Logistic Regression - Cardic Muscle Cells-----------------------\n")
print("\nAccuracy:\n", accuracy)
print("\nConfusion Matrix:\n", CM)
print("\nClassification Report:\n", CR)


# In[ ]:





# ## Support Vector Machine

# In[19]:


from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

# Identify Cardiac Muscle Cells from the dataset
cardiac_muscle_cells = adata.obs['cell_type'] == 'cardiac muscle cell'

# Create a Binary label for cardic muscle cells
adata.obs['is_cardiac_muscle'] = cardiac_muscle_cells.astype(int)

# Extract features (gene expressions) and Label to X and y variables respectively
X_svm = adata.X
y_svm = adata.obs['is_cardiac_muscle']

# Spliting data into train and test sets with train_test_split, # training data: 80%, testing data: 20% 
X_train_svm, X_test_svm, y_train_svm, y_test_svm = train_test_split(X_svm, y_svm, test_size=0.2, random_state=42)

#Instantiate Support Vector Machine model
SVM_Model = SVC(kernel ='linear', C=1.0)

#Train the model
SVM_Model.fit(X_train_svm, y_train_svm)

# Predict Cardiac muscle cells test data
y_pred_svm = SVM_Model.predict(X_test_svm)

print("\n\n Predicted target: 'cardiac muscle cell: SVM'\n\n", y_pred_svm)


# In[20]:


# Evaluate SVM Model performance
accuracy_svm = accuracy_score(y_test_svm, y_pred_svm)
CM_svm = confusion_matrix(y_test_svm, y_pred_svm)
CR_svm = classification_report(y_test_svm, y_pred_svm)

print("Logistic Regression - Cardic Muscle Cells-----------------------\n")
print("\nAccuracy:\n", accuracy_svm)
print("\nConfusion Matrix:\n", CM_svm)
print("\nClassification Report:\n", CR_svm)


# In[ ]: