all_data raw_data = pd.DataFrame()
for filename in all_files:
df = pd.[pd.read_csv(filename, index_col='Date', header=0)
all_data header=0) for filename in all_files]
raw_data = pd.concat([all_data, df], axis=0)
print(f'size before: {len(df.index)}')
# Remove dupli
# https://stackoverflow.com/questions/13035764/remove-pandas-rows-with-duplicate-indices/14900065#14900065
df = df[~df.index.duplicated(keep='first')]
#
df.to_csv("filename.concat(raw_data, axis=0)
print(f'Size: {raw_data.shape[0]}')
raw_data.to_csv("raw_data.csv", index = False, header=True)index=False)
{"html5":"htmlmixed","css":"css","javascript":"javascript","php":"php","python":"python","ruby":"ruby","lua":"text\/x-lua","bash":"text\/x-sh","go":"go","c":"text\/x-csrc","cpp":"text\/x-c++src","diff":"diff","latex":"stex","sql":"sql","xml":"xml","apl":"apl","asterisk":"asterisk","c_loadrunner":"text\/x-csrc","c_mac":"text\/x-csrc","coffeescript":"text\/x-coffeescript","csharp":"text\/x-csharp","d":"d","ecmascript":"javascript","erlang":"erlang","groovy":"text\/x-groovy","haskell":"text\/x-haskell","haxe":"text\/x-haxe","html4strict":"htmlmixed","java":"text\/x-java","java5":"text\/x-java","jquery":"javascript","mirc":"mirc","mysql":"sql","ocaml":"text\/x-ocaml","pascal":"text\/x-pascal","perl":"perl","perl6":"perl","plsql":"sql","properties":"text\/x-properties","q":"text\/x-q","scala":"scala","scheme":"text\/x-scheme","tcl":"text\/x-tcl","vb":"text\/x-vb","verilog":"text\/x-verilog","yaml":"text\/x-yaml","z80":"text\/x-z80"}
