We Keep Coding

Extract letters after $ symbol using Pandas

I am trying to extract just the data upto and including the $ symbol from a spreadsheet.
I have isolated the data to give me just the column containing the data but what I am trying to do is extract any and all symbols that follow a $ symbol.
For example:
$AAPL $LOW $TSLA and so on from the entire dataset but I don't need or want $1000 $600 and so on - just letters only and either a period or a space follows but just the characters a-z is what I am trying to get.
I haven't been successful in full extraction and my code is starting to get messy so I'll provide the code that will bring back the data for you to see for yourself. I am using Jupyter Notebook.
import mysql.connector
import pandas
googleSheedID = '15fhpxqWDRWkNtEFhi9bQyWUg8pDn4B-R2N18s1xFYTU'
worksheetName = 'Sheet1'
URL = 'https://docs.google.com/spreadsheets/d/{0}/gviz/tq?tqx=out:csv&sheet={1}'.format(
googleSheedID,
worksheetName
)
df = pandas.read_csv(URL)
del df['DATE']
del df['USERNAME']
del df['LINK']
del df['LINK2']
df[df["TWEET"].str.contains("RT")==False]
print(df)

Not sure if I understand what you want correctly, but the following codes give all elements that comes after $ before (blank space).
import mysql.connector
import pandas
googleSheedID = '15fhpxqWDRWkNtEFhi9bQyWUg8pDn4B-R2N18s1xFYTU'
worksheetName = 'Sheet1'
URL = 'https://docs.google.com/spreadsheets/d/{0}/gviz/tq?tqx=out:csv&sheet={1}'.format(
googleSheedID,
worksheetName
)
df = pandas.read_csv(URL)
del df['DATE']
del df['USERNAME']
del df['LINK']
del df['LINK2']
unique_results = []
for i in range(len(df['TWEET'])):
if 'RT' in df["TWEET"][i]:
continue
else:
for j in range(len(df['TWEET'][i])-1):
if df['TWEET'][i][j] == '$':
if df['TWEET'][i][j+1] == '1' or df['TWEET'][i][j+1] == '2' or df['TWEET'][i][j+1] == '3' or\
df['TWEET'][i][j+1] == '4' or df['TWEET'][i][j+1] == '5' or df['TWEET'][i][j+1] == '6' or\
df['TWEET'][i][j+1] == '7' or df['TWEET'][i][j+1] == '8' or df['TWEET'][i][j+1] == '9' or df['TWEET'][i][j+1] == '0':
continue
else:
start = j
for k in range(start, len(df['TWEET'][i])):
if df['TWEET'][i][k] == ' ' or df['TWEET'][i][k:k+1] == '\n':
end = k
break
results = df['TWEET'][i][start:end]
if results not in unique_results:
unique_results.append(results)
print(unique_results)
edit: fixed the code
The outputs are:
['$GME', '$SNDL', '$FUBO', '$AMC', '$LOTZ', '$CLOV', '$USAS', '$AIHS', '$PLM', '$LODE', '$TTNP', '$IMTE', '', '$NAK.', '$NAK', '$CRBP', '$AREC', '$NTEC', '$NTN', '$CBAT', '$ZYNE', '$HOFV', '$GWPH', '$KERN', '$ZYNE,', '$AIM', '$WWR', '$CARV', '$VISL', '$SINO', '$NAKD', '$GRPS', '$RSHN', '$MARA', '$RIOT', '$NXTD', '$LAC', '$BTC', '$ITRM', '$CHCI', '$VERU', '$GMGI', '$WNBD', '$KALV', '$EGOC', '$Veru', '$MRNA', '$PVDG', '$DROP', '$EFOI', '$LLIT', '$AUVI', '$CGIX', '$RELI', '$TLRY', '$ACB', '$TRCH', '$TRCH.', '$TSLA', '$cciv', '$sndl', '$ANCN', '$TGC', '$tlry', '$KXIN', '$AMZN', '$INFI', '$LMND', '$COMS', '$VXX', '$LEDS', '$ACY', '$RHE', '$SINO.', '$GPL', '$SPCE', '$OXY', '$CLSN', '$FTFT', '$FTFT.....', '$BIEI', '$EDRY', '$CLEU', '$FSR', '$SPY', '$NIO', '$LI', '$XPEV,', '$UL', '$RGLG', '$SOS', '$QS', '$THCB', '$SUNW', '$MICT', '$BTC.X', '$T', '$ADOM', '$EBON', '$CLPS', '$HIHO', '$ONTX', '$WNRS', '$SOLO', '$Mara,', '$Riot,', '$SOS,', '$GRNQ,', '$RCON,', '$FTFT,', '$BTBT,', '$MOGO,', '$EQOS,', '$CCNC', '$CCIV', '$tsla', '$fsr', '$wkhs', '$ride', '$nio', '$NETE', '$DPW', '$MOSY', '$SSNT', '$PLTR', '$GSAH:', '$EQOS', '$MTSL', '$CMPS', '$CHIF', '$MU', '$HST', '$SNAP', '$CTXR', '$acy', '$FUBOTV', '$DPBE', '$HYLN', '$SPOT', '$NSAV', '$HYLN,', '$aabb', '$AAL', '$BBIG', '$ITNS', '$CTIB', '$AMPG', '$ZI', '$NUVI', '$INTC', '$TSM', '$AAPL', '$MRJT', '$RCMT', '$IZEA', '$BBIG,', '$ARKK', '$LIAUTO', '$MARA:', '$SOS:', '$XOM', '$ET', '$BRNW', '$SYPR', '$LCID', '$QCOM', '$FIZZ', '$TRVG', '$SLV', '$RAFA', '$TGCTengasco,', '$BYND', '$XTNT', '$NBY', '$sos', '$KMPH', '$', '$(0.60)', '$(0.64)', '$BIDU', '$rkt', '$GTT', '$CHUC', '$CLF', '$INUV', '$RKT', '$COST', '$MDCN', '$HCMC', '$UWMC', '$riot', '$OVID', '$HZON', '$SKT', '$FB', '$PLUG', '$BA', '$PYPL', '$PSTH.', '$NVDA', '$AMPG.', '$aese.', '$spy', '$pltr', '$MSFT', '$AMD', '$QQQ', '$LTNC', '$WKHS', '$EYES', '$RMO', '$GNUS', '$gme', '$mdmp', '$kern', '$AEI', '$BABA', '$YALA', '$TWTR', '$WISH', '$GE', '$ORCL', '$JUPW', '$TMBR', '$SSYS', '$NKE', '$AMPGAmpliTech', '$$$', '$$', '$RGLS', '$HOGE', '$GEGR', '$nclh', '$IGAC', '$FCEL', '$TKAT', '$OCG', '$YVR', '$IPDN.', '$IPDN', "$SINO's", '$WIMI', '$TKAT.', '$BAC', '$LZR', '$LGHL', '$F', '$GM', '$KODK', '$atvk', '$ATVK', '$AIKI', '$DS', '$AI', '$WTII', '$oxy', '$DYAI', '$DSS', '$ZKIN', '$MFH', '$WKEY', '$MKGI', '$DLPN', '$PSWW', '$SNOW', '$ALYA', '$AESE', '$CSCW', '$CIDM', '$HOFV.', '$LIVX', '$FNKO', '$HPR', '$BRQS', '$GIGM', '$APOP', '$EA', '$CUEN', '$TMBR?', '$FLNT,', '$APPS', '$METX', '$STG', '$WSRC', '$AMHC', '$VIAC', '$MO', '$UAVL', '$CS', '$MDT', '$GYST', '$CBBT', '$ASTC', '$AACG', '$WAFU.', '$WAFU', '$CASI', '$mmmw', '$MVIS', '$SNOA', '$C', '$KR', '$EWZ', '$VALE', '$EWZ.', '$CSCO', '$PINS', '$XSPA', '$VPRX', '$CEMI', '$M', '$BMRA', '$SPX', '$akt', '$SURG', '$NCLH', '$ARSN', '$ODT', '$SGBX', '$CRWD.', '$TGRR', '$PENN', '$BB', '$XOP', '$XL', '$FREQ', '$IDRA', '$DKNG', '$COHN', '$ADHC', '$ISWH', '$LEGO', '$OTRA', '$NAAC', '$HCAR', '$PPGH', '$SDAC', '$PNTM', '$OUST', '$IO', '$HQGE', '$HENC', '$KYNC', '$ATNF', '$BNSO', '$HDSN', '$AABB', '$SGH', '$BMY', '$VERY', '$EARS', '$ROKU', '$PIXY', '$APRE', '$SFET', '$SQ', '$EEIQ', '$REDU', '$CNWT', '$NFLX', '$RGBPP', '$RGBP', '$SHOP', '$VITL', '$RAAS', '$CPNG', '$JKS', '$COMP', '$NAFS']

You can use regular expressions.
\$[a-zA-Z]+
After reading the df execute the below code
import re
# Create Empty list for final results
results = []
final_results = []
for row_num in range(len(df['TWEET'])):
string_to_check = df['TWEET'][row_num]
# Check for RT at the beginning of the string only.
# if 'RT' in df["TWEET"][row_num] would have found the "RT" anywhere in the string.
if re.match(r"^RT", string_to_check):
continue
else:
# Check for all words starting with $ and followed by only alphabets.
# This will find $FOOBAR but not $600, $6FOOBAR & $FOO6BAR
rel_text_l = re.findall(r"\$[a-zA-Z]+", string_to_check)
# Check for empty list
if rel_text_l:
# Add elements of list to another list directly
results.extend(rel_text_l)
# Making list of the set of list to remove duplicates
final_results = list(set(results))
print(results)
print(final_results)
The results are
['$GME', '$FOOBAR', '$FOO', '$SNDL', '$FUBO', '$AMC', '$GME', '$LOTZ', '$CLOV', '$USAS', '$GOBLIN', '$LTNC']
['$LTNC', '$GOBLIN', '$AMC', '$FOO', '$FOOBAR', '$LOTZ', '$CLOV', '$SNDL', '$GME', '$USAS', '$FUBO']
Notice that $GME is removed once in final_results
If you were not bothered about remove tweets starting with RT, all this could be achieved in one line of code.
direct_result = list(set(re.findall(r"\$[a-zA-Z]+", str(df['TWEET']))))

error with regex matching over 2 source files, expected string or buffer

so I would like to from a input.txt file, create a two dictionaries
for example, here is sample of the input.txt file
#. VAR #first=Billy
#. VAR #last=Bob
#. PRINT VARS
#. VAR #petName=Gato
#. VAR #street="1234 Home Street"
#. VAR #city="New York"
#. VAR #state=NY
#. VAR #zip=21236
#. VAR #title=Dr.
#. PRINT VARS
#. FORMAT LM=5 JUST=LEFT
#. PRINT FORMAT
so VAR #varName=value
i.e in the case of #first=Billy you would get something like varDict = {"first": "Billy"} right?
Now I wanna know how to do that thru the entire file
There are two dictionaries that I would need to populate, one for the variables, and one for FORMAT, which just holds values, doesn't actually do anything for now.
As far as a desired output, In the input file, there are commands that when read, will trigger to either add variables to the directory, or print that directory, or add to the format directory. I would use the pprint function like this pprint.pprint(varDict , width=30) and would output something like this
{'first': 'Billy',
'last': 'Bob'}
{'city': 'New York',
'first': 'Billy',
'last': 'Bob',
'petName': 'Gato',
'state': 'NY',
'street': '1234 Home Street',
'title': 'Dr.',
'zip': '21236'}
{'BULLET': 'o',
'FLOW': 'YES',
'JUST': 'LEFT',
'LM': '5',
'RM': '80'}
Unfortunately i keep getting errors all over the place on the driver and source file
AttributeError: 'list' object has no attribute 'groups'
TypeError: expected string or buffer
Driver.py
input=(sys.argv[1])
# Group 1. VAR
# Group 2. #first=Mae or JUST=RIGHT FLOW=NO
# pass Group 2 as atString
regexSearch = re.compile(r'^#. ([A-Z]+) (.*)', re.MULTILINE)
regexPrintVAR = re.compile(r'^#\.\s*PRINT\s(VARS)', re.MULTILINE)
regexPrintFORMAT = re.compile(r'^#\.\s*PRINT\s(FORMAT)',re.MULTILINE)
regexERRCheck = re.compile(r'^#\.\s*FORMAT\s+BAD', re.MULTILINE)
varDictionary = dict()
formatDictionary = {"FLOW":"YES", "LM":"1", "RM":"80","JUST":"LEFT","BULLET":"o"}
file = open(input, "r")
while True:
inputLine = file.readline()
matchObj = regexSearch.search(inputLine)
command, atString = matchObj.groups()
if command == "VAR":
setVariable(atString,varDictionary)
if command == "FORMAT":
formatListERR = regexERRCheck.search(inputLine)
if formatListERR != None:
print("*** Not a recognizable command")
line = file.readline()
setFormat(atString, formatDictionary)
if command == "PRINT":
printVARObj = regexPrintVAR.search(inputLine)
printFormatObj = regexPrintFORMAT.search(inputLine)
if printVARObj != None:
pprint.pprint(varDictionary, width=30)
elif printFormatObj != None:
pprint.pprint(formatDict, width=30)
inputLine = file.readline()
file.close()
importFileIUse.py
# The atString is the remainder of the string after the VAR or FORMAT key word.
varDictionary = dict()
formatDictionary = {"FLOW":"YES", "LM":"1", "RM":"80","JUST":"LEFT","BULLET":"o"}
def setFormat(atString,formatDictionary):
regexFormat = re.compile(r'((?:(?:\w+)=(?:\w+)\s*)*)$')
line = re.split(" +", atString)
formatList = regexFormat.search(line)
if formatList:
for param in formatList[0].split():
splitParam = param.split('=')
formatDictionary[splitParam[0]] = splitParam[1]
def setVariable (atString, varDictionary):
regexVAR = re.compile(r'#(\w+)=(\w+|.*)\s*$', re.MULTILINE)
# file = open(input)
# line = file.readline()
# line = re.split(" +", atString)
#while line:
varList = regexVAR.findall(atString)
for key, value in varList:
varDictionary[key] = value

When using os.startfile file is not found

import os # Tuo os moduuli
print("Valitse suoritettava luokka:"); #Tulosta...
print("1 = Kertolasku");
print("2 = Osamaara");
print("3 = Vertailu");
print("4 = Floydin kolmio");
print("5 = Kertotaulu");
print("6 = Viikonpaiva");
print("7 = Rivit");
v = int(input("Valitse:")) # v = seuraava numero
if v == 1: # jos v on yhtäkuin 1 niin avaa...
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x01.bat')
if v == 2:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x02.bat')
if v == 3:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x03.bat')
if v == 4:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x04.bat')
if v == 5:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x05.bat')
if v == 21:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x06.bat') #Secret
if v == 1942:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x07.bat') #Secret
if v == 6:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x08.bat')
if v == 7:
os.startfile(r'%USERPROFILE%\Desktop\JAVA\BATCH\x09.bat')
else: # muutoin tulosta...
print ("VIRHE - Onko syötetty luku 1-5? Onko JAVA kansio sijainnissa %USERPROFILE%\Desktop ?");
print ("VIRHE - Onko Java asennettu? Onko OS = Windows?");
print ("VIRHE - Onko Java:n path variable asetettu oikein?");
input('Paina ENTER sammuttaaksesi...') #Lisää sulkeva komento.
This code returns the following error:
Error message
I have checked that file named x01.bat exists in:%USERPROFILE%\Desktop\JAVA\BATCH
I have tried to replace \ with / but windows doesn't recognize / as an way to access a directory.
I have tried to escape the backslash with another backslash. It only makes the same error with three backslashes instead of 2. (Yes I removed r before ' when I escaped a backslash with a backslash.)
I even tried to escape a backslash with a backslash before a backslash but error is the same with more backslashes.
Verdict: It seems that Python 3.6 on Windows 10 wants to add a backslash before a backslash no matter what I do. Because of that windows doesn't know where the .bat file is.
Any help is appreciated, please share your ideas!

For constructing paths in python, it is generally easier to use os.path.join
So something like
os.startfile(os.path.join(os.environ['USERPROFILE'], 'Desktop', 'JAVA', 'BATCH', 'x01.bat'))

Using Tuple for Inserting into Command

I'm trying to get this script to take the contents of the tuple and cycle through using a for loop (I'm not sure where to put it in my code) and put the contents of the tuple in a command. For this example I've used find as the command. Depending on which option the executor uses sp1 or sp2 will determine how much of the tuple will be used.
import sys, subprocess, os, string
cmd = '/bin/find '
tuple = ('apple', 'banana', 'cat', 'dog')
sp1 = tuple[0:1]
sp2 = tuple[2:3]
def find():
find_cmd = subprocess.Popen(cmd + " * -name {}".format(type)),
stdout=subprocess.PIPE,
stderr=subprocess.PIPE, shell=True)
output, err = find_cmd.communicate()
find = output
find_temp = []
find_temp = string.split(find)
if find_temp[0] == ' ':
print("Found nothing")
else:
print("Found {}".format(find_temp))
type_input = input("Are you looking for fruit or animals? ")
if type_input == "fruit":
type = sp1
elif type_input == "animals":
type = sp2
print("syntax error")
exit()
find()

You're close, but you don't do what you're trying to do, that's just silly. You could do better.
Rather than doing this weird tuple slicing thing, just give them a real name:
import sys, subprocess, os, string
# No need for the trailing space here
FIND = '/bin/find'
fruit = ('apple', 'banana')
animals = ('cat', 'dog')
Alternatively, you could use a dictionary:
find_params = {
'fruit': ['apple', 'banana'],
'animals': ['cat', 'dog'],
}
In your comment you mentioned:
my tuple is a bit larger and both variables use some of the same values...
This would keep me from typing many of the same values into two separate lists.
You can still take a nice approach:
cheeses = ('Wensleydale', 'Edam', 'Cheddar', 'Gouda')
spam = ('Spam with eggs', 'Spam on eggs', 'Spam')
confectionaries = ('crunchy frog', 'spring surprise', 'cockroach cluster',
'anthrax ripple', 'cherry fondue')
food = cheeses + spam + confectionaries
Even if you just need a subset, you can still do something like:
food = cheeses + spam[:2] + confectionaries[-1:]
You should take parameter(s) for your find command instead. Also, no need to concatenate and then use a format string. Just use a format string for all the things:
def find(what, cmd=FIND):
find_cmd = subprocess.Popen('{cmd} * -name {what}'.format(cmd=cmd, what=what),
stdout=subprocess.PIPE,
stderr=subprocess.PIPE, shell=True)
output, err = find_cmd.communicate()
find = output
find_temp = []
find_temp = string.split(find)
if find_temp[0] == ' ':
print("Found nothing")
else:
print("Found {}".format(find_temp))
Now you can either use the variables, or what they asked for:
type_input = input("Are you looking for fruit or animals? ")
try:
find(find_params[type_input])
except KeyError:
sys.exit('Unknown parameter {!r}'.format(type_input))
# Or use the variables
if type_input == "fruit":
find(fruit)
elif type_input == "animals":
find(animals)
else:
sys.exit('Unknown parameter {!r}'.format(type_input))

Edit keys from a python object - getting TypeError: iteration over non-sequence

When I print out my variable
print myOptions
I get
{'verbose': False,
'number': '1',
'asgMaxSize': '?dev = 2 | ?qa = 2 | ? prd = 8',
'availabilityZone': 'us-east-1a,us-east-1e',
'securityGroups': ['bouncebox-member', 'bouncebox-member'],
'\
instanceType': '?dev = m3.medium | ?qa = m3.medium | ?prd = m3.medium',
'runcommon': False,
'zone': 'inpwrd.net',
'bubblewrapp': False,
'healthCheckTarget': 'HTTP:8080/:NAME:/api/health-check',
'environment': 'dev',
'application': 'tint',
'nscustomerdata': None,
'ami': 'ami-8a5d81e2',
'userData': 'defaultUserData.txt',
'outputFile': None,
'description': 'tint - replacement thumbscraper stack',
'desiredCapacity': '1',
'securityPorts': 'httpPort8080,sshPort',
'instanceProfile': 'default-:ENV:1',
'elbListeners': 'http8080',
'name': 'tint',
'blockDeviceMap': 'Empty',
'instanceMonitoring': 'false',
'asgMinSize': '1',
'keyname': None,
'alarms': 'diskspace,memory,tint'}
(line breaks added for readability)
So it looks like a key/value pair to me. I want to iterate through it like this:
for key in myOptions:
if key == "instanceProfile":
myOptions.value = myOptions.value.replace(":ENV:", "dev")
But when I run the code I get "TypeError: iteration over non-sequence"
So, how do I determine what Type the object is and how can I walk through the key/value pair (dictionary?) that is there?
I am using python version 2.7.8 if that make a difference.
When I print out "print myOptions.class" I get "optparse.Values"
The construction of myOptions is
from optparse import OptionParser
_opt = OptionParser("%prog [options] configfiles...")
_opt.add_option("-v", "--verbose", ...)
_opt.add_option("-r", "--runcommon", ...)
.... a bunch of _opt.add_option
import shlex
def parse(filename, defaults):
myopt, args = _opt.parse_args(shlex.split(open(filename).read()), defaults)
return myopt
if __name__ == "__main__":
import sys
myOptions, args = _opt.parse_args()
myOptions = parse("default.ini", myOptions)
for arg in args:
myOptions = parse(arg, myOptions)
myOptions, args = _opt.parse_args(values = myOptions)
argConfigurationName = args[-1]
if (myOptions.name == None):
myOptions.name = argConfigurationName
if myOptions.verbose == True:
print "Configuration Variables"
for name in _opt.defaults:
print "\t", name, "=", getattr(myOptions, name)