@@ -6,10 +6,21 @@ output: html_document
 ---
 
 ```{r "knitr config", cache = FALSE, include=FALSE}
-require("knitr")
-knitr::opts_knit$set(root.dir = "C:/Github/Programming_Data_Science/ourdata")
-#lh_root
+#nico
+#require("knitr")
+#knitr::opts_knit$set(root.dir = "C:/Github/Programming_Data_Science/ourdata")
+
+
+#Philipp_roots
 #knitr::opts_knit$set(root.dir = "C:\\Users\\Philipp\\Documents\\StudDocs\\Master\\SS2019\\Programming Data Science\\data")
+
+#lh_roots
+##surface
+#knitr::opts_knit$set(root.dir = "C:/Github/Programming_Data_Science/ourdata")
+
+##desktop
+knitr::opts_knit$set(root.dir = "F:\\Laure\\Documents\\git hub Repositories\\phyk_data")
+
 ```
 ```{r setup, include=FALSE}
 knitr::opts_chunk$set(echo = TRUE)
@@ -73,7 +84,7 @@ for (i in 1:ncol(dataframe)) {
     }
   }
 }
-# Lösche doppelte Spalten (immer die 2.)
+# L?sche doppelte Spalten (immer die 2.)
 dataframe <- subset(dataframe, select = -drop)
 head(dataframe)
 ```
 
@@ -37,12 +37,12 @@ def delete_empty_indexorcolumns_in_df(df,index_or_columns,threshold):
 
 
 def clean_df_generic(df,threshold):
-    print(df)
+    #print(df)
     index_or_columns = "columns"
     df = delete_empty_indexorcolumns_in_df(df,index_or_columns,threshold)
     index_or_columns = "index"
     df = delete_empty_indexorcolumns_in_df(df,index_or_columns,threshold)
-    print(df)
+    #print(df)
     return df
 
 
@@ -69,11 +69,11 @@ def merge_columns(df,column_name1,column_name2):
 
 #order 
 df = read_data.load_dataframe("order.pkl")
-df = clean_df_generic(df,1)
+df = clean_df_generic(df,0)
 
 #clickstream
 df2 = read_data.load_dataframe("click.pkl")
-df2 = clean_df_generic(df2,1)
+df2 = clean_df_generic(df2,0)
 
 
 
 
@@ -0,0 +1,47 @@
+import os.path
+import zipfile
+import os
+import csv
+import shutil
+from zipfile import ZipFile
+from absolute_data_paths import relative_to_absolute
+
+def extra_zip_to(filename,destination):
+    filename = relative_to_absolute(filename)
+    with ZipFile(filename,"r") as zip:
+        zfile = zip.namelist()[0]
+        zip.extract(zfile,destination)
+
+
+def identify_and_tret(source_folder,filename):
+        path_file = source_folder+"\\"+filename
+        ending = filename.split(".")[1]
+        if ending =="txt":
+                shutil.copy(path_file,relative_to_absolute("../01_data_understanding"))
+        elif ending =="csv":
+                shutil.copy(path_file,relative_to_absolute("../00_raw_data"))
+        elif ending =="zip":
+                extra_zip_to(path_file,relative_to_absolute("../00_raw_data"))
+
+
+
+
+def get_files_from_folder(source_folder):
+    folderpath = relative_to_absolute(source_folder)
+    for path,list_folder,list_filename in os.walk(folderpath):
+        if path == folderpath and list_folder == []:
+            for row in list_filename:
+                    identify_and_tret(folderpath,row)               
+
+
+def copy_into_raw_data_and_data_understanding():
+        #clickstream
+        clickstream_path = "../clickstream"
+        get_files_from_folder(clickstream_path)
+        #order
+        order_path = "../orders"
+        get_files_from_folder(order_path)
+
+
+
+