我是一名大学生，他并不真正理解我在做什么，但是当我在我的 jupyter 笔记本中输入 install.packages("ggplot2") 时，我收到错误 警告信息： “无法访问存储库的索引https://cran.r-project.org/bin/windows/contrib/3.6： 无法打开 URL 'https://cran.r-project.org/bin/windows/contrib/3.6/PACKAGES'"仅以源代码形式提供的包，并且可能需要 C/C++/Fortran 编译：'cli' 'farver' 'isoband' 'rlang' '鳞片' 'tibble' 'vctrs' 这些不会被安装 安装源包“pillar”、“lifecycle”、“ggplot2”
install.packages(“ggplot2”)中的警告消息： “安装包‘lifecycle’的退出状态为非零”install.packages(“ggplot2”)中的警告消息： “安装包‘pillar’的退出状态为非零”install.packages（“ggplot2”）中的警告消息： “包‘ggplot2’的安装具有非零退出状态”
当我试图寻找答案时，我真的无法弄清楚。
我使用的笔记本版本是6.5.4 服务器运行在这个版本的 Python 上： Python 3.11.5 |由 Anaconda, Inc. 包装 | （主要，2023 年 9 月 11 日，13:26:23）[MSC v.1916 64 位 (AMD64)]
如果有人可以帮助（非常！）易于遵循的说明，那就太好了。 我尝试安装 tidyverse, install.packages("ggplot2", source="type") 并得到相同的错误。
提前致谢！
如果有人可以帮助（非常！）易于遵循的说明，那就太好了。 我尝试安装 tidyverse, install.packages("ggplot2", source="type") 并得到相同的错误。
ANASTYLE
`def cure_cols(df, filename):
for col in df.columns:
if df[col].nunique() <= 5 and df[col].dtype.kind == 'O':
df.drop(col, axis = 1, inplace = True)
elif df[col].nunique() == 0:
df.drop(col, axis = 1, inplace = True)
if 'vector' in filename:
df = pd.DataFrame(df.iloc[:, 1])
return df`
`def cure_rows(df_column):
df_column = df_column.values
for row in range(len(df_column)):
try:
df_column[row] = df_column[row].astype(np.int64)
except:
try:
df_column[row] = df_column[row].astype(np.float64)
except:
df_column[row] = np.nan
return df_column`
`def sound_handle(data, sr):
data_1s = np.ndarray((len(data) // sr, 4))
for t in range(0, len(data) // sr):
data_1s[t] = [np.mean(data[sr*t: sr*(t+1)]), np.min(data[sr*t: sr*(t+1)]),
np.max(data[sr*t: sr*(t+1)]), np.std(data[sr*t: sr*(t+1)])]
return pd.DataFrame(data_1s)
`(https://ru.wikipedia.org/wiki/%D0%94%D0%B5%D0%B9%D1%81%D1%82%D0%B2%D1%83%D1%8E%D1%89%D0%B5%D0%B5_%D0%B7%D0%BD%D0%B0%D1%87%D0%B5%D0%BD%D0%B8%D0%B5_%D0%BF%D0%B5%D1%80%D0%B5%D0%BC%D0%B5%D0%BD%D0%BD%D0%BE%D0%B3%D0%BE_%D1%82%D0%BE%D0%BA%D0%B0)
`
def el_handle(df, hz):
df_1 = np.ndarray((len(df) // hz))
for t in range(0, len(df) // hz):
df_1[t] = np.sqrt(1/hz * df.iloc[t*hz: (t+1)*hz].apply(lambda x: x**2).sum())
#df_1[t] = df.iloc[t*hz: (t+1)*hz].abs().mean()
return pd.DataFrame(df_1)`
`for experiment in range(1, 10):
temp_df = pd.DataFrame()
for filename in table_exp['
File name'][table_exp["№"] == experiment]:
if table_exp['В в э?'][table_exp['
File name'] == filename].values[0] == 'no':
continue
print('в о: ', filename)
if filename.split('.')[-1] == 'csv':
if table_exp['Decoding'][table_exp['
File name'] == filename].values in \
['Т', "Н"]:
df = pd.read_csv(filedir + '/' + filename, header = None, skiprows = 5, dtype = np.float32)
else:
df = pd.read_csv(filedir + '/' + filename, header = None, skiprows = 1)
elif filename.split('.')[-1] == 'xlsx':
print('Excel!')
elif filename.split('.')[-1] == 'wav':
sr = table_exp['sampling rate'][table_exp['
File name'] == filename].values[0]
data, sr = librosa.load(filedir + '/' + filename, sr = sr)
with open(' ' + str(experiment) + '_raw_audio.pkl', 'wb') as file:
pickle.dump([data, sr], file)
df = sound_handle(data, sr)
df = cure_cols(df, filename)
df = memory_cut(df, filename)
if table_exp['Decoding'][table_exp['
File name'] == filename].values in \
['Т', "Н"]:
df = el_handle(df, \
table_exp['sampling rate'][table_exp['
File name'] == filename].values[0])
if filename.split('.')[-1] != 'wav':
if filename[:2] == 't_':
df.columns = ['coolant temperature']
else:
df.columns = table_exp['Decoding'][table_exp['
File name'] == filename].values
else:
df.columns = ['mean', 'max', 'min', 'std']
if filename[:2] == 't_':
df.iloc[:, 0].interpolate(inplace = True)
length = df.iloc[:, 0].shape[0]
temp_df = pd.concat([temp_df, df], axis = 1)
temp_df['experiment'] = experiment
temp_df = temp_df.iloc[:length]
temp_df.to_pickle('' + str(experiment) + '_df.pkl')
mem = temp_df.memory_usage(deep = True).sum() / (1024**3)
del temp_df
print(f'experiment #{experiment} processed', np.round(mem, 1))`
`def combine_experiments():
temp_df = pd.DataFrame()
for experiment in range(1, 10):
df = pd.read_pickle('' + str(experiment) + '_df.pkl')
temp_df = pd.concat([temp_df, df], axis = 0)
temp_df.sort_values(['experiment'])
return temp_df.reset_index()
df = combine_experiments()
df`
`def nan_handle(df):
df.fillna(method = 'ffill', inplace = True)
df.fillna(method = 'bfill', inplace = True)
return df`
`for exp in range(1, 10):
df = pd.read_pickle(r'D:\КЗ\КЗ\dataset' + str(experiment) + '_df.pkl')
df = nan_handle(df)
df.to_pickle(r'D:\КЗ\КЗ\dataset' + str(experiment) + '_df.pkl')`
`def combine_experiments():
dfs = []
for experiment in range(1, 10):
df = pd.read_pickle(r'D:\КЗ\КЗ\dataset' + str(experiment) + '_df.pkl')
dfs.append(df)
temp_df = pd.concat(dfs, axis=0)
temp_df = temp_df.sort_values(['experiment'])
return temp_df.reset_index(drop=True)
df = combine_experiments()
`
def combine_experiments():
temp_df = pd.DataFrame()
for experiment in range(1, 10):
df = pd.read_pickle('' + str(experiment) + '_df.pkl')
temp_df = pd.concat([temp_df, df], axis = 0)
temp_df.sort_values(['experiment'])
return temp_df.reset_index()
df = combine_experiments()
df`
`def nan_handle(df):
df.fillna(method = 'ffill', inplace = True)
df.fillna(method = 'bfill', inplace = True)
return df`
`for exp in range(1, 10):
df = pd.read_pickle(r'' + str(experiment) + '_df.pkl')
df = nan_handle(df)
df.to_pickle(r' + str(experiment) + '_df.pkl')`