Почему эта ошибка отображается, хотя лист Excel имеет рабочий лист и не поврежден? ⇐ Python

[Anonymous]

Пытаемся сопоставить данные из двух листов с определенным соглашением об именах. Код может идентифицировать файлы Excel, но продолжает возвращать: Study Test/Purticipant 1/text_export_P1S1T2.xlsx: индекс рабочего листа 0 недействителен, найдено 0 рабочих листов.
Ниже приведен код что я использовал:

Код: Выделить всё

import pandas as pd
import numpy as np
import os
from scipy.interpolate import interp1d
from datetime import datetime
import warnings

# Suppress specific warnings
warnings.filterwarnings("ignore", category=UserWarning, module='openpyxl')

# Directory containing the participant folders
home_dir = os.getcwd()

# Standardized increment and stance phase conversion
X2 = np.linspace(0, 100, 101)  # Standardized to 101 points for interpolation

# Prepare to collect results in a single DataFrame
consolidated_results = []

def process_file(filepath):
# Load Excel file
try:
df = pd.read_excel(filepath, skiprows=9, engine='openpyxl')
except Exception as e:
print(f"Error reading {filepath}: {e}")
return None  # Return None if there's an error

# Check if expected columns are present
if df.shape[1] < 51:  # Ensure there are at least 51 columns
print(f"Expected columns not found in {filepath}. Found columns: {df.shape[1]}")
return None

# Extract relevant columns
T = df.iloc[:, 1].dropna().values  # Time (s)
COP1x = df.iloc[:, 49].dropna().values  # Filtered COP x (mm)
COP1y = df.iloc[:, 50].dropna().values  # Filtered COP y (mm)

# Normalize time to 0-100 for Stance Phase
if len(T) < 2:  # Need at least two points to calculate min and max
print(f"Not enough time points in {filepath}. Found points: {len(T)}")
return None

Tmin, Tmax = np.min(T), np.max(T)
SP = (T - Tmin) * (100 / (Tmax - Tmin))

# Interpolate data
interp_func = lambda y: interp1d(SP, y, kind='cubic', fill_value="extrapolate")(X2)
return {
'Stance Phase (%)': X2,
'COP1x (mm)': interp_func(COP1x),
'COP1y (mm)': interp_func(COP1y)
}

participants = [
1, 3, 4, 6, 7, 8, 9, 10, 11, 12
]

# Iterate through each participant folder and process files
for participant in participants:
participant_folder = f"Participant {participant}"
participant_path = os.path.join(home_dir, participant_folder)

for file in os.listdir(participant_path):
if file.startswith("text_export") and file.endswith(".xlsx"):
# Process file
filepath = os.path.join(participant_path, file)
processed_data = process_file(filepath)

if processed_data is not None:  # Only append if processing was successful
# Append data to consolidated results
for i in range(len(processed_data['COP1x (mm)'])):
consolidated_results.append({
'COP1x (mm)': processed_data['COP1x (mm)'][i],
'COP1y (mm)': processed_data['COP1y (mm)'][i]
})

# Convert the results to a DataFrame and save to an Excel file
if consolidated_results:  # Only save if there's data to save
consolidated_df = pd.DataFrame(consolidated_results)
output_filename = f"Consolidated_Results_{datetime.now().strftime('%y%m%d')}.xlsx"
consolidated_df.to_excel(output_filename, index=False)
print(f"Consolidated data saved to {output_filename}")
else:
print("No data to save.")

Я пытался создать тестовый файл Excel, чтобы проверить, не связана ли это с моей пандой, но мне удалось создать файл Excel.

Подробнее здесь: https://stackoverflow.com/questions/791 ... is-not-cor