LC

app.py

@@ -1,12 +1,12 @@
 import numpy as np
 import pickle
 import pandas as pd
-import requests
-from selenium import webdriver
+# import requests
+# from selenium import webdriver
 import matplotlib.pyplot as plt
 #Simple assignment
-from selenium.webdriver import Firefox
-from selenium.webdriver.common.keys import Keys
+# from selenium.webdriver import Firefox
+# from selenium.webdriver.common.keys import Keys
 from selenium.common.exceptions import NoSuchElementException
 import requests 
 import os
@@ -20,73 +20,73 @@ import streamlit as st
 ### Scrap the cosmic id information
 # ### FRAMEWORKS NEEDED
 
-def scrap():
-            #### Setting options to the driver
-            options = webdriver.FirefoxOptions()
-            options.add_argument('--headless')
-            options.add_argument('--no-sandbox')
-            options.add_argument('--disable-dev-shm-usage')
-            options.capabilities
-            ### Setting options of webdriver
-            # a) Setting the chromedriver
-            browser = Firefox(options=options,executable_path=r"C:\Users\Pablo\OneDrive\Documents\Documentos\Escuela Politécnica Superior Leganés\4 AÑO\ASIGNATURAS\1 CUATRI\WEB ANALYTICS\PART 2\Milestone3\geckodriver.exe")
-            ### Functions and execution to run the scrapping
-
-
-            def getinfofromtable(oddrows:list,score:float,headertable)->list:
-                    rows = []
-                    for row in oddrows:
-                        cols = []
-                        for (i,col) in enumerate(row.find_elements_by_css_selector("td")):
-                            if  i==headertable.index( 'Primary Tissue') or  i==headertable.index('Primary Histology') or i==headertable.index('Zygosity'):
-                                cols.append(col.text)
-                        cols.append(score)
-                        rows.append(cols)
-                    return rows            
-            def getinfocosmic(mutationid):
-                    import time
-                    search = browser.find_element_by_id('search-field')
-                    search = search.find_element_by_class_name("text_def")
-                    search.send_keys(mutationid)
-                    search.send_keys(Keys.RETURN)
-                    time.sleep(5)
-                    try:
-                        container = browser.find_element_by_id("section-list")
+# def scrap():
+            # #### Setting options to the driver
+            # options = webdriver.FirefoxOptions()
+            # options.add_argument('--headless')
+            # options.add_argument('--no-sandbox')
+            # options.add_argument('--disable-dev-shm-usage')
+            # options.capabilities
+            # ### Setting options of webdriver
+            # # a) Setting the chromedriver
+            # browser = Firefox(options=options,executable_path=r"C:\Users\Pablo\OneDrive\Documents\Documentos\Escuela Politécnica Superior Leganés\4 AÑO\ASIGNATURAS\1 CUATRI\WEB ANALYTICS\PART 2\Milestone3\geckodriver.exe")
+            # ### Functions and execution to run the scrapping
+
+
+            # def getinfofromtable(oddrows:list,score:float,headertable)->list:
+            #         rows = []
+            #         for row in oddrows:
+            #             cols = []
+            #             for (i,col) in enumerate(row.find_elements_by_css_selector("td")):
+            #                 if  i==headertable.index( 'Primary Tissue') or  i==headertable.index('Primary Histology') or i==headertable.index('Zygosity'):
+            #                     cols.append(col.text)
+            #             cols.append(score)
+            #             rows.append(cols)
+            #         return rows            
+            # def getinfocosmic(mutationid):
+            #         import time
+            #         search = browser.find_element_by_id('search-field')
+            #         search = search.find_element_by_class_name("text_def")
+            #         search.send_keys(mutationid)
+            #         search.send_keys(Keys.RETURN)
+            #         time.sleep(5)
+            #         try:
+            #             container = browser.find_element_by_id("section-list")
                     
-                    except NoSuchElementException:
-                        return []
+            #         except NoSuchElementException:
+            #             return []
                     
-                    try:
+            #         try:
 
-                        subq1 = container.text[container.text.find("score")+len("score"):]
-                        score = float(subq1[:subq1.find(")")].strip())
-                    except ValueError:
-                        score = 0 
+            #             subq1 = container.text[container.text.find("score")+len("score"):]
+            #             score = float(subq1[:subq1.find(")")].strip())
+            #         except ValueError:
+            #             score = 0 
                     
 
 
-                    section = browser.find_element_by_id("DataTables_Table_0")
+            #         section = browser.find_element_by_id("DataTables_Table_0")
 
 
-                    headertable = [header.text for header in section.find_element_by_tag_name("thead").find_elements_by_tag_name("th")]
+            #         headertable = [header.text for header in section.find_element_by_tag_name("thead").find_elements_by_tag_name("th")]
 
-                    oddrows = section.find_elements_by_class_name("odd")
-                    evenrows = section.find_elements_by_class_name("even")
+            #         oddrows = section.find_elements_by_class_name("odd")
+            #         evenrows = section.find_elements_by_class_name("even")
 
-                    l1 = getinfofromtable(oddrows,score,headertable)
-                    l1.extend(getinfofromtable(evenrows,score,headertable))
+            #         l1 = getinfofromtable(oddrows,score,headertable)
+            #         l1.extend(getinfofromtable(evenrows,score,headertable))
                     
-                    # browser.close()
-                    return l1
-                    ## Looking for cosmic id info
-                    cosl = []
-                    browser.get("https://cancer.sanger.ac.uk/cosmic")
-                    for cos in cosmicinfo.reset_index()["COSMIC_ID"].iloc[20:]:
-                            if cos.find(",")!=-1:
-                                    cos = cos.split(",")[0]
-
-                            cosl.append(getinfocosmic(cos))
-                            browser.get("https://cancer.sanger.ac.uk/cosmic")
+            #         # browser.close()
+            #         return l1
+            #         ## Looking for cosmic id info
+            #         cosl = []
+            #         browser.get("https://cancer.sanger.ac.uk/cosmic")
+            #         for cos in cosmicinfo.reset_index()["COSMIC_ID"].iloc[20:]:
+            #                 if cos.find(",")!=-1:
+            #                         cos = cos.split(",")[0]
+
+            #                 cosl.append(getinfocosmic(cos))
+            #                 browser.get("https://cancer.sanger.ac.uk/cosmic")
 ### Pieplots
 def pieplot(merging,id=0):
     genecount = merging.groupby(by=["gene_name","UV_exposure_tissue","sampleID"]).count().reset_index()