Python beginner. I don't know how to solve this error occurred with the code below:TypeError: '>' not supported between instances of 'str' and 'float'
Question:
I’m following the tutorial on YouTube called Python programming for Finance. I’ve checked multiple times if I’ve wrote the same code of the YouTuber but I couldn’t find any error on the transcription. Could you help me in finding the error?
import numpy as np
import pandas as pd
import pickle
from collections import Counter
def process_data_for_labels(ticker):
hm_days = 7
df = pd.read_csv('sp500_joined_closes.csv', index_col=0)
tickers = df.columns.values.tolist()
df.fillna(0,inplace=True)
for i in range(1, hm_days+1):
df['{}_{}d'.format(ticker, i)] = (df[ticker].shift(-i) - df[ticker]) / df[ticker]
df.fillna(0, inplace= True)
return tickers, df
def buy_sell_hold(*args):
cols = [c for c in args]
requirement = 0.02
for col in cols:
if col > requirement:
return 1
if col < -requirement:
return -1
return 0
def extract_featuresets(ticker):
tickers, df = process_data_for_labels(ticker)
# df['{}_target'.format(ticker)] = list(map(buy_sell_hold,df[[c for c in df.columns if c not in tickers]].values))
df['{}_target'.format(ticker)] = list(map(buy_sell_hold,
df['{}_1d'.format(ticker)],
df['{}_2d'.format(ticker)],
df['{}_3d'.format(ticker)],
df['{}_4d'.format(ticker)],
df['{}_5d'.format(ticker)],
df['{}_6d'.format(ticker)],
df['{}_7d'.format(ticker)]))
vals = df['{}_target'.format(ticker)].values.tolist()
str_vals = [str(i) for i in vals]
print('Data spread:', Counter(str_vals))
df.fillna(0,inplace=True)
df=df.replace([np.inf,-np.inf], np.nan)
df.dropna(inplace=True)
df_vals = df[[ticker for ticker in tickers]].pct_change()
df_vals = df_vals.replace([np.inf,-np.inf], 0)
df_vals.fillna(0,inplace=True)
X = df_vals.values
Y = df['{}_target'.format(ticker)].values
return X,Y, df
extract_featuresets('AAPL')
this is the error if col > requirement:
TypeError: ‘>’ not supported between instances of ‘str’ and ‘float’
Answers:
Well you’re doing a comparison between two differents types : A string and a Float.
You can convert the string variable using :
number = float(string)
So i your case :
def buy_sell_hold(*args):
cols = [c for c in args]
requirement = 0.02
for col in cols:
if float(col) > requirement:
return 1
if float(col) < -requirement:
return -1
return 0
But make sure that the args only contains float or add a try catch around the conditions.
I’m following the tutorial on YouTube called Python programming for Finance. I’ve checked multiple times if I’ve wrote the same code of the YouTuber but I couldn’t find any error on the transcription. Could you help me in finding the error?
import numpy as np
import pandas as pd
import pickle
from collections import Counter
def process_data_for_labels(ticker):
hm_days = 7
df = pd.read_csv('sp500_joined_closes.csv', index_col=0)
tickers = df.columns.values.tolist()
df.fillna(0,inplace=True)
for i in range(1, hm_days+1):
df['{}_{}d'.format(ticker, i)] = (df[ticker].shift(-i) - df[ticker]) / df[ticker]
df.fillna(0, inplace= True)
return tickers, df
def buy_sell_hold(*args):
cols = [c for c in args]
requirement = 0.02
for col in cols:
if col > requirement:
return 1
if col < -requirement:
return -1
return 0
def extract_featuresets(ticker):
tickers, df = process_data_for_labels(ticker)
# df['{}_target'.format(ticker)] = list(map(buy_sell_hold,df[[c for c in df.columns if c not in tickers]].values))
df['{}_target'.format(ticker)] = list(map(buy_sell_hold,
df['{}_1d'.format(ticker)],
df['{}_2d'.format(ticker)],
df['{}_3d'.format(ticker)],
df['{}_4d'.format(ticker)],
df['{}_5d'.format(ticker)],
df['{}_6d'.format(ticker)],
df['{}_7d'.format(ticker)]))
vals = df['{}_target'.format(ticker)].values.tolist()
str_vals = [str(i) for i in vals]
print('Data spread:', Counter(str_vals))
df.fillna(0,inplace=True)
df=df.replace([np.inf,-np.inf], np.nan)
df.dropna(inplace=True)
df_vals = df[[ticker for ticker in tickers]].pct_change()
df_vals = df_vals.replace([np.inf,-np.inf], 0)
df_vals.fillna(0,inplace=True)
X = df_vals.values
Y = df['{}_target'.format(ticker)].values
return X,Y, df
extract_featuresets('AAPL')
this is the error if col > requirement:
TypeError: ‘>’ not supported between instances of ‘str’ and ‘float’
Well you’re doing a comparison between two differents types : A string and a Float.
You can convert the string variable using :
number = float(string)
So i your case :
def buy_sell_hold(*args):
cols = [c for c in args]
requirement = 0.02
for col in cols:
if float(col) > requirement:
return 1
if float(col) < -requirement:
return -1
return 0
But make sure that the args only contains float or add a try catch around the conditions.