def describe(df, bins=10, check_correlation=True, correlation_threshold=0.9, correlation_overrides=None, check_recoded=False, pool_size=multiprocessing.cpu_count(), **kwargs):
"""Generates a dict containing summary statistics for a given dataset stored as a pandas `DataFrame`.
Used has is it will output its content as an HTML report in a Jupyter notebook.
Parameters
----------
df : DataFrame
Data to be analyzed
bins : int
Number of bins in histogram.
The default is 10.
check_correlation : boolean
Whether or not to check correlation.
It's `True` by default.
correlation_threshold: float
Threshold to determine if the variable pair is correlated.
The default is 0.9.
correlation_overrides : list
Variable names not to be rejected because they are correlated.
There is no variable in the list (`None`) by default.
check_recoded : boolean
Whether or not to check recoded correlation (memory heavy feature).
Since it's an expensive computation it can be activated for small datasets.
`check_correlation` must be true to disable this check.
It's `False` by default.
pool_size : int
Number of workers in thread pool
The default is equal to the number of CPU.
Returns
-------
dict
Containing the following keys:
* table: general statistics on the dataset
* variables: summary statistics for each variable
* freq: frequency table
Notes:
------
* The section dedicated to check the correlation should be externalized
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
try:
# reset matplotlib style before use
# Fails in matplotlib 1.4.x so plot might look bad
matplotlib.style.use("default")
except:
pass
matplotlib.style.use(resource_filename(__name__, "pandas_profiling.mplstyle"))
# Clearing the cache before computing stats
base.clear_cache()
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
kwargs.update({'bins': bins})
# Describe all variables in a univariate way
if pool_size == 1:
local_multiprocess_func = partial(multiprocess_func, **kwargs)
ldesc = {col: s for col, s in map(local_multiprocess_func, df.iteritems())}
else:
pool = multiprocessing.Pool(pool_size)
local_multiprocess_func = partial(multiprocess_func, **kwargs)
ldesc = {col: s for col, s in pool.map(local_multiprocess_func, df.iteritems())}
pool.close()
# Get correlations
dfcorrPear = df.corr(method="pearson")
dfcorrSpear = df.corr(method="spearman")
# Check correlations between variable
if check_correlation is True:
''' TODO: corr(x,y) > 0.9 and corr(y,z) > 0.9 does not imply corr(x,z) > 0.9
If x~y and y~z but not x~z, it would be better to delete only y
Better way would be to find out which variable causes the highest increase in multicollinearity.
'''
corr = dfcorrPear.copy()
for x, corr_x in corr.iterrows():
if correlation_overrides and x in correlation_overrides:
continue
for y, corr in corr_x.iteritems():
if x == y: break
if corr > correlation_threshold:
ldesc[x] = pd.Series(['CORR', y, corr], index=['type', 'correlation_var', 'correlation'])
if check_recoded:
categorical_variables = [(name, data) for (name, data) in df.iteritems() if base.get_vartype(data)=='CAT']
for (name1, data1), (name2, data2) in itertools.combinations(categorical_variables, 2):
if correlation_overrides and name1 in correlation_overrides:
continue
confusion_matrix=pd.crosstab(data1,data2)
if confusion_matrix.values.diagonal().sum() == len(df):
ldesc[name1] = pd.Series(['RECODED', name2], index=['type', 'correlation_var'])
# Convert ldesc to a DataFrame
names = []
ldesc_indexes = sorted([x.index for x in ldesc.values()], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
# General statistics
table_stats = {}
table_stats['n'] = len(df)
table_stats['nvar'] = len(df.columns)
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (table_stats['n'] * table_stats['nvar'])
unsupported_columns = variable_stats.transpose()[variable_stats.transpose().type != base.S_TYPE_UNSUPPORTED].index.tolist()
table_stats['n_duplicates'] = sum(df.duplicated(subset=unsupported_columns)) if len(unsupported_columns) > 0 else 0
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize / table_stats['n'])
table_stats.update({k: 0 for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE", "CORR", "RECODED", "BOOL", "UNSUPPORTED")})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
table_stats['REJECTED'] = table_stats['CONST'] + table_stats['CORR'] + table_stats['RECODED']
return {
'table': table_stats,
'variables': variable_stats.T,
'freq': {k: (base.get_groupby_statistic(df[k])[0] if variable_stats[k].type != base.S_TYPE_UNSUPPORTED else None) for k in df.columns},
'correlations': {'pearson': dfcorrPear, 'spearman': dfcorrSpear}
}
def describe(df, **kwargs):
"""
Generates a object containing summary statistics for a given DataFrame
:param df: DataFrame to be analyzed
:param bins: Number of bins in histogram
:return: Dictionary containing
table: general statistics on the DataFrame
variables: summary statistics for each variable
freq: frequency table
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
bins = kwargs.get('bins', 10)
try:
# reset matplotlib style before use
# Fails in matplotlib 1.4.x so plot might look bad
matplotlib.style.use("default")
except:
pass
matplotlib.style.use(resource_filename(__name__, "pandas_profiling.mplstyle"))
def pretty_name(x):
x *= 100
if x == int(x):
return '%.0f%%' % x
else:
return '%.1f%%' % x
def describe_numeric_1d(series, base_stats):
stats = {'mean': series.mean(), 'std': series.std(), 'variance': series.var(), 'min': series.min(),
'max': series.max()}
stats['range'] = stats['max'] - stats['min']
for x in np.array([0.05, 0.25, 0.5, 0.75, 0.95]):
stats[pretty_name(x)] = series.quantile(x)
stats['iqr'] = stats['75%'] - stats['25%']
stats['kurtosis'] = series.kurt()
stats['skewness'] = series.skew()
stats['sum'] = series.sum()
stats['mad'] = series.mad()
stats['cv'] = stats['std'] / stats['mean'] if stats['mean'] else np.NaN
stats['type'] = "NUM"
stats['n_zeros'] = (len(series) - np.count_nonzero(series))
stats['p_zeros'] = stats['n_zeros'] / len(series)
# Large histogram
imgdata = BytesIO()
plot = series.plot(kind='hist', figsize=(6, 4),
facecolor='#337ab7', bins=bins) # TODO when running on server, send this off to a different thread
plot.figure.subplots_adjust(left=0.15, right=0.95, top=0.9, bottom=0.1, wspace=0, hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
stats['histogram'] = 'data:image/png;base64,' + quote(base64.b64encode(imgdata.getvalue()))
#TODO Think about writing this to disk instead of caching them in strings
plt.close(plot.figure)
stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def mini_histogram(series):
# Small histogram
imgdata = BytesIO()
plot = series.plot(kind='hist', figsize=(2, 0.75), facecolor='#337ab7', bins=bins)
plot.axes.get_yaxis().set_visible(False)
plot.set_axis_bgcolor("w")
xticks = plot.xaxis.get_major_ticks()
for tick in xticks[1:-1]:
tick.set_visible(False)
tick.label.set_visible(False)
for tick in (xticks[0], xticks[-1]):
tick.label.set_fontsize(8)
plot.figure.subplots_adjust(left=0.15, right=0.85, top=1, bottom=0.35, wspace=0, hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
result_string = 'data:image/png;base64,' + quote(base64.b64encode(imgdata.getvalue()))
plt.close(plot.figure)
return result_string
def describe_date_1d(series, base_stats):
stats = {'min': series.min(), 'max': series.max()}
stats['range'] = stats['max'] - stats['min']
stats['type'] = "DATE"
# TODO: Matplotlib can't do histograms of dates.
# stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def describe_categorical_1d(data):
# Only run if at least 1 non-missing value
objcounts = data.value_counts()
top, freq = objcounts.index[0], objcounts.iloc[0]
names = []
result = []
if data.dtype == object or com.is_categorical_dtype(data.dtype):
names += ['top', 'freq', 'type']
result += [top, freq, 'CAT']
return pd.Series(result, index=names, name=data.name)
def describe_constant_1d(data):
return pd.Series(['CONST'], index=['type'], name=data.name)
def describe_unique_1d(data):
return pd.Series(['UNIQUE'], index=['type'], name=data.name)
def describe_1d(data):
count = data.count()
leng = len(data)
distinct_count = data.nunique(dropna=False)
if count > distinct_count > 1:
mode = data.mode().iloc[0]
else:
mode = data[0]
results_data = {'count': count, 'distinct_count': distinct_count, 'p_missing': 1 - count / leng,
'n_missing': leng - count,
'is_unique': distinct_count == leng,
'mode': mode,
'p_unique': distinct_count / count}
try:
# pandas 0.17 onwards
results_data['memorysize'] = data.memory_usage()
except:
results_data['memorysize'] = 0
result = pd.Series(results_data, name=data.name)
if distinct_count <= 1:
result = result.append(describe_constant_1d(data))
elif com.is_numeric_dtype(data):
result = result.append(describe_numeric_1d(data, result))
elif com.is_datetime64_dtype(data):
result = result.append(describe_date_1d(data, result))
elif distinct_count == leng:
result = result.append(describe_unique_1d(data))
else:
result = result.append(describe_categorical_1d(data))
return result
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
# Describe all variables in a univariate way
ldesc = {col: describe_1d(s) for col, s in df.iteritems()}
# Check correlations between variables
''' TODO: corr(x,y) > 0.9 and corr(y,z) > 0.9 does not imply corr(x,z) > 0.9
If x~y and y~z but not x~z, it would be better to delete only y
Better way would be to find out which variable causes the highest increase in multicollinearity.
'''
corr = df.corr()
for x, corr_x in corr.iterrows():
for y, corr in corr_x.iteritems():
if x == y: break
if corr > 0.9:
ldesc[x] = pd.Series(['CORR', y, corr], index=['type', 'correlation_var', 'correlation'], name=x)
# Convert ldesc to a DataFrame
names = []
ldesc_indexes = sorted([x.index for x in ldesc.values()], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
# General statistics
table_stats = {'n': len(df), 'nvar': len(df.columns)}
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (table_stats['n'] * table_stats['nvar'])
table_stats['n_duplicates'] = sum(df.duplicated())
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize / table_stats['n'])
table_stats.update({k: 0 for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE", "CORR")})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
table_stats['REJECTED'] = table_stats['CONST'] + table_stats['CORR']
return {'table': table_stats, 'variables': variable_stats.T, 'freq': {k: df[k].value_counts() for k in df.columns}}
def describe(df,
bins=10,
correlation_overrides=None,
pool_size=multiprocessing.cpu_count(),
**kwargs):
"""
Generates a object containing summary statistics for a given DataFrame
:param df: DataFrame to be analyzed
:param bins: Number of bins in histogram
:param correlation_overrides: Variable names not to be rejected because they are correlated
:param pool_size: Number of workers in thread pool
:return: Dictionary containing
table: general statistics on the DataFrame
variables: summary statistics for each variable
freq: frequency table
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
try:
# reset matplotlib style before use
# Fails in matplotlib 1.4.x so plot might look bad
matplotlib.style.use("default")
except:
pass
matplotlib.style.use(
resource_filename(__name__, "pandas_profiling.mplstyle"))
def pretty_name(x):
x *= 100
if x == int(x):
return '%.0f%%' % x
else:
return '%.1f%%' % x
def describe_numeric_1d(series, base_stats):
stats = {
'mean': series.mean(),
'std': series.std(),
'variance': series.var(),
'min': series.min(),
'max': series.max()
}
stats['range'] = stats['max'] - stats['min']
for x in np.array([0.05, 0.25, 0.5, 0.75, 0.95]):
stats[pretty_name(x)] = series.dropna().quantile(
x
) # The dropna() is a workaround for https://github.com/pydata/pandas/issues/13098
stats['iqr'] = stats['75%'] - stats['25%']
stats['kurtosis'] = series.kurt()
stats['skewness'] = series.skew()
stats['sum'] = series.sum()
stats['mad'] = series.mad()
stats['cv'] = stats['std'] / stats['mean'] if stats['mean'] else np.NaN
stats['type'] = "NUM"
stats['n_zeros'] = (len(series) - np.count_nonzero(series))
stats['p_zeros'] = stats['n_zeros'] / len(series)
# Histograms
stats['histogram'] = histogram(series)
stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def _plot_histogram(series,
figsize=(6, 4),
facecolor='#337ab7',
bins=bins):
"""Plot an histogram from the data and return the AxesSubplot object.
Parameters
----------
series: Series, default None
The data to plot
figsize: a tuple (width, height) in inches, default (6,4)
The size of the figure.
facecolor: str
The color code.
bins: int, default
The number of equal-width bins in the given range.
Returns
-------
matplotlib.AxesSubplot, The plot.
"""
if com.is_datetime64_dtype(series):
# TODO: These calls should be merged
fig = plt.figure(figsize=figsize)
plot = fig.add_subplot(111)
plot.set_ylabel('Frequency')
try:
plot.hist(series.values, facecolor=facecolor, bins=bins)
except TypeError: # matplotlib 1.4 can't plot dates so will show empty plot instead
pass
else:
plot = series.plot(
kind='hist', figsize=figsize, facecolor=facecolor, bins=bins
) # TODO when running on server, send this off to a different thread
return plot
def histogram(series):
"""Plot an histogram of the data.
Parameters
----------
series: Series, default None
The data to plot.
Returns
-------
str, The resulting image encoded as a string.
"""
imgdata = BytesIO()
plot = _plot_histogram(series)
plot.figure.subplots_adjust(left=0.15,
right=0.95,
top=0.9,
bottom=0.1,
wspace=0,
hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
result_string = 'data:image/png;base64,' + quote(
base64.b64encode(imgdata.getvalue()))
# TODO Think about writing this to disk instead of caching them in strings
plt.close(plot.figure)
return result_string
def mini_histogram(series):
"""Plot a small (mini) histogram of the data.
Parameters
----------
series: Series, default None
The data to plot.
Returns
-------
str, The resulting image encoded as a string.
"""
imgdata = BytesIO()
plot = _plot_histogram(series, figsize=(2, 0.75))
plot.axes.get_yaxis().set_visible(False)
plot.set_axis_bgcolor("w")
xticks = plot.xaxis.get_major_ticks()
for tick in xticks[1:-1]:
tick.set_visible(False)
tick.label.set_visible(False)
for tick in (xticks[0], xticks[-1]):
tick.label.set_fontsize(8)
plot.figure.subplots_adjust(left=0.15,
right=0.85,
top=1,
bottom=0.35,
wspace=0,
hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
result_string = 'data:image/png;base64,' + quote(
base64.b64encode(imgdata.getvalue()))
plt.close(plot.figure)
return result_string
def describe_date_1d(series, base_stats):
stats = {'min': series.min(), 'max': series.max()}
stats['range'] = stats['max'] - stats['min']
stats['type'] = "DATE"
stats['histogram'] = histogram(series)
stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def describe_categorical_1d(data):
# Only run if at least 1 non-missing value
objcounts = data.value_counts()
top, freq = objcounts.index[0], objcounts.iloc[0]
names = []
result = []
if data.dtype == object or com.is_categorical_dtype(data.dtype):
names += ['top', 'freq']
result += [top, freq]
return pd.Series(result, index=names, name=data.name)
def describe_constant_1d(data):
return pd.Series(['CONST'], index=['type'], name=data.name)
def describe_unique_1d(data):
return pd.Series(['UNIQUE'], index=['type'], name=data.name)
def describe_1d(data):
leng = len(data) # number of observations in the Series
count = data.count() # number of non-NaN observations in the Series
# Replace infinite values with NaNs to avoid issues with
# histograms later.
data.replace(to_replace=[np.inf, np.NINF, np.PINF],
value=np.nan,
inplace=True)
n_infinite = count - data.count(
) # number of infinte observations in the Series
distinct_count = data.nunique(
dropna=False) # number of unique elements in the Series
if count > distinct_count > 1:
mode = data.mode().iloc[0]
else:
mode = data[0]
results_data = {
'count': count,
'distinct_count': distinct_count,
'p_missing': 1 - count / leng,
'n_missing': leng - count,
'p_infinite': n_infinite / leng,
'n_infinite': n_infinite,
'is_unique': distinct_count == leng,
'mode': mode,
'p_unique': distinct_count / count
}
try:
# pandas 0.17 onwards
results_data['memorysize'] = data.memory_usage()
except:
results_data['memorysize'] = 0
result = pd.Series(results_data, name=data.name)
if distinct_count <= 1:
result = result.append(describe_constant_1d(data))
elif com.is_numeric_dtype(data):
result = result.append(describe_numeric_1d(data, result))
elif com.is_datetime64_dtype(data):
result = result.append(describe_date_1d(data, result))
elif distinct_count == leng:
result = result.append(describe_unique_1d(data))
else:
result = result.append(describe_categorical_1d(data))
result['type'] = 'CAT'
return result
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
# Describe all variables in a univariate way
pool = multiprocessing.Pool(pool_size)
local_multiprocess_func = partial(multiprocess_func, **kwargs)
ldesc = {
col: s
for col, s in pool.map(local_multiprocess_func, df.iteritems())
}
pool.close()
# Check correlations between variables
''' TODO: corr(x,y) > 0.9 and corr(y,z) > 0.9 does not imply corr(x,z) > 0.9
If x~y and y~z but not x~z, it would be better to delete only y
Better way would be to find out which variable causes the highest increase in multicollinearity.
'''
corr = df.corr()
for x, corr_x in corr.iterrows():
if correlation_overrides and x in correlation_overrides:
continue
for y, corr in corr_x.iteritems():
if x == y: break
if corr > 0.9:
ldesc[x] = pd.Series(
['CORR', y, corr],
index=['type', 'correlation_var', 'correlation'],
name=x)
# Convert ldesc to a DataFrame
names = []
ldesc_indexes = sorted([x.index for x in ldesc.values()], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
# General statistics
table_stats = {'n': len(df), 'nvar': len(df.columns)}
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (
table_stats['n'] * table_stats['nvar'])
table_stats['n_duplicates'] = sum(df.duplicated())
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize /
table_stats['n'])
table_stats.update(
{k: 0
for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE", "CORR")})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
table_stats['REJECTED'] = table_stats['CONST'] + table_stats['CORR']
return {
'table': table_stats,
'variables': variable_stats.T,
'freq': {k: df[k].value_counts()
for k in df.columns}
}
def describe(df, **kwargs):
"""
Generates a object containing summary statistics for a given DataFrame
:param df: DataFrame to be analyzed
:param bins: Number of bins in histogram
:return: Dictionary containing
table: general statistics on the DataFrame
variables: summary statistics for each variable
freq: frequency table
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
bins = kwargs.get('bins', 10)
try:
# reset matplotlib style before use
# Fails in matplotlib 1.4.x so plot might look bad
matplotlib.style.use("default")
except:
pass
matplotlib.style.use(
resource_filename(__name__, "pandas_profiling.mplstyle"))
def pretty_name(x):
x *= 100
if x == int(x):
return '%.0f%%' % x
else:
return '%.1f%%' % x
def describe_numeric_1d(series, base_stats):
stats = {
'mean': series.mean(),
'std': series.std(),
'variance': series.var(),
'min': series.min(),
'max': series.max()
}
stats['range'] = stats['max'] - stats['min']
for x in np.array([0.05, 0.25, 0.5, 0.75, 0.95]):
stats[pretty_name(x)] = series.quantile(x)
stats['iqr'] = stats['75%'] - stats['25%']
stats['kurtosis'] = series.kurt()
stats['skewness'] = series.skew()
stats['sum'] = series.sum()
stats['mad'] = series.mad()
stats['cv'] = stats['std'] / stats['mean'] if stats['mean'] else np.NaN
stats['type'] = "NUM"
stats['n_zeros'] = (len(series) - np.count_nonzero(series))
stats['p_zeros'] = stats['n_zeros'] / len(series)
# Large histogram
imgdata = BytesIO()
plot = series.plot(
kind='hist', figsize=(6, 4), facecolor='#337ab7', bins=bins
) # TODO when running on server, send this off to a different thread
plot.figure.subplots_adjust(left=0.15,
right=0.95,
top=0.9,
bottom=0.1,
wspace=0,
hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
stats['histogram'] = 'data:image/png;base64,' + quote(
base64.b64encode(imgdata.getvalue()))
#TODO Think about writing this to disk instead of caching them in strings
plt.close(plot.figure)
stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def mini_histogram(series):
# Small histogram
imgdata = BytesIO()
plot = series.plot(kind='hist',
figsize=(2, 0.75),
facecolor='#337ab7',
bins=bins)
plot.axes.get_yaxis().set_visible(False)
plot.set_axis_bgcolor("w")
xticks = plot.xaxis.get_major_ticks()
for tick in xticks[1:-1]:
tick.set_visible(False)
tick.label.set_visible(False)
for tick in (xticks[0], xticks[-1]):
tick.label.set_fontsize(8)
plot.figure.subplots_adjust(left=0.15,
right=0.85,
top=1,
bottom=0.35,
wspace=0,
hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
result_string = 'data:image/png;base64,' + quote(
base64.b64encode(imgdata.getvalue()))
plt.close(plot.figure)
return result_string
def describe_date_1d(series, base_stats):
stats = {'min': series.min(), 'max': series.max()}
stats['range'] = stats['max'] - stats['min']
stats['type'] = "DATE"
# TODO: Matplotlib can't do histograms of dates.
# stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def describe_categorical_1d(data):
# Only run if at least 1 non-missing value
objcounts = data.value_counts()
top, freq = objcounts.index[0], objcounts.iloc[0]
names = []
result = []
if data.dtype == object or com.is_categorical_dtype(data.dtype):
names += ['top', 'freq', 'type']
result += [top, freq, 'CAT']
return pd.Series(result, index=names, name=data.name)
def describe_constant_1d(data):
return pd.Series(['CONST'], index=['type'], name=data.name)
def describe_unique_1d(data):
return pd.Series(['UNIQUE'], index=['type'], name=data.name)
def describe_1d(data):
count = data.count()
leng = len(data)
distinct_count = data.nunique(dropna=False)
if count > distinct_count > 1:
mode = data.mode().iloc[0]
else:
mode = data[0]
results_data = {
'count': count,
'distinct_count': distinct_count,
'p_missing': 1 - count / leng,
'n_missing': leng - count,
'is_unique': distinct_count == leng,
'mode': mode,
'p_unique': distinct_count / count
}
try:
# pandas 0.17 onwards
results_data['memorysize'] = data.memory_usage()
except:
results_data['memorysize'] = 0
result = pd.Series(results_data, name=data.name)
if distinct_count <= 1:
result = result.append(describe_constant_1d(data))
elif com.is_numeric_dtype(data):
result = result.append(describe_numeric_1d(data, result))
elif com.is_datetime64_dtype(data):
result = result.append(describe_date_1d(data, result))
elif distinct_count == leng:
result = result.append(describe_unique_1d(data))
else:
result = result.append(describe_categorical_1d(data))
return result
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
# Describe all variables in a univariate way
ldesc = {col: describe_1d(s) for col, s in df.iteritems()}
# Check correlations between variables
''' TODO: corr(x,y) > 0.9 and corr(y,z) > 0.9 does not imply corr(x,z) > 0.9
If x~y and y~z but not x~z, it would be better to delete only y
Better way would be to find out which variable causes the highest increase in multicollinearity.
'''
corr = df.corr()
for x, corr_x in corr.iterrows():
for y, corr in corr_x.iteritems():
if x == y: break
if corr > 0.9:
ldesc[x] = pd.Series(
['CORR', y, corr],
index=['type', 'correlation_var', 'correlation'],
name=x)
# Convert ldesc to a DataFrame
names = []
ldesc_indexes = sorted([x.index for x in ldesc.values()], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
# General statistics
table_stats = {'n': len(df), 'nvar': len(df.columns)}
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (
table_stats['n'] * table_stats['nvar'])
table_stats['n_duplicates'] = sum(df.duplicated())
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize /
table_stats['n'])
table_stats.update(
{k: 0
for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE", "CORR")})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
table_stats['REJECTED'] = table_stats['CONST'] + table_stats['CORR']
return {
'table': table_stats,
'variables': variable_stats.T,
'freq': {k: df[k].value_counts()
for k in df.columns}
}
def describe(df,
bins=10,
correlation_overrides=None,
pool_size=multiprocessing.cpu_count(),
**kwargs):
"""
Generates a object containing summary statistics for a given DataFrame
:param df: DataFrame to be analyzed
:param bins: Number of bins in histogram
:param correlation_overrides: Variable names not to be rejected because they are correlated
:param pool_size: Number of workers in thread pool
:return: Dictionary containing
table: general statistics on the DataFrame
variables: summary statistics for each variable
freq: frequency table
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
try:
# reset matplotlib style before use
# Fails in matplotlib 1.4.x so plot might look bad
matplotlib.style.use("default")
except:
pass
matplotlib.style.use(
resource_filename(__name__, "pandas_profiling.mplstyle"))
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
# Describe all variables in a univariate way
pool = multiprocessing.Pool(pool_size)
local_multiprocess_func = partial(multiprocess_func, **kwargs)
ldesc = {
col: s
for col, s in pool.map(local_multiprocess_func, df.iteritems())
}
pool.close()
# Check correlations between variables
''' TODO: corr(x,y) > 0.9 and corr(y,z) > 0.9 does not imply corr(x,z) > 0.9
If x~y and y~z but not x~z, it would be better to delete only y
Better way would be to find out which variable causes the highest increase in multicollinearity.
'''
corr = df.corr()
for x, corr_x in corr.iterrows():
if correlation_overrides and x in correlation_overrides:
continue
for y, corr in corr_x.iteritems():
if x == y: break
if corr > 0.9:
ldesc[x] = pd.Series(
['CORR', y, corr],
index=['type', 'correlation_var', 'correlation'])
categorical_variables = [(name, data) for (name, data) in df.iteritems()
if get_vartype(data) == 'CAT']
for (name1,
data1), (name2,
data2) in itertools.combinations(categorical_variables, 2):
if correlation_overrides and name1 in correlation_overrides:
continue
confusion_matrix = pd.crosstab(data1, data2)
if confusion_matrix.values.diagonal().sum() == len(df):
ldesc[name1] = pd.Series(['RECODED', name2],
index=['type', 'correlation_var'])
# Convert ldesc to a DataFrame
names = []
ldesc_indexes = sorted([x.index for x in ldesc.values()], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
# General statistics
table_stats = {'n': len(df), 'nvar': len(df.columns)}
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (
table_stats['n'] * table_stats['nvar'])
table_stats['n_duplicates'] = sum(df.duplicated())
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize /
table_stats['n'])
table_stats.update({
k: 0
for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE", "CORR", "RECODED")
})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
table_stats['REJECTED'] = table_stats['CONST'] + table_stats[
'CORR'] + table_stats['RECODED']
return {
'table': table_stats,
'variables': variable_stats.T,
'freq': {k: df[k].value_counts()
for k in df.columns}
}
def describe(df):
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
# reset matplotlib style before use
matplotlib.style.use("default")
matplotlib.style.use(resource_filename(__name__, "pandas_profiling.mplstyle"))
def pretty_name(x):
x *= 100
if x == int(x):
return '%.0f%%' % x
else:
return '%.1f%%' % x
def describe_numeric_1d(series, base_stats):
stats = {'mean': series.mean(), 'std': series.std(), 'variance': series.var(), 'min': series.min(),
'max': series.max()}
stats['range'] = stats['max'] - stats['min']
for x in np.array([0.05, 0.25, 0.5, 0.75, 0.95]):
stats[pretty_name(x)] = series.quantile(x)
stats['iqr'] = stats['75%'] - stats['25%']
stats['kurtosis'] = series.kurt()
stats['skewness'] = series.skew()
stats['sum'] = series.sum()
stats['mad'] = series.mad()
stats['cv'] = stats['std'] / stats['mean'] if stats['mean'] else np.NaN
stats['type'] = "NUM"
stats['p_zeros'] = (len(series) - np.count_nonzero(series)) / len(series)
# Large histogram
imgdata = BytesIO()
plot = series.plot(kind='hist', figsize=(6, 4),
facecolor='#337ab7') # TODO when running on server, send this off to a different thread
plot.figure.subplots_adjust(left=0.15, right=0.95, top=0.9, bottom=0.1, wspace=0, hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
stats['histogram'] = 'data:image/png;base64,' + quote(base64.b64encode(imgdata.getvalue()))
#TODO Think about writing this to disk instead of caching them in strings
plt.close(plot.figure)
stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def mini_histogram(series):
# Small histogram
imgdata = BytesIO()
plot = series.plot(kind='hist', figsize=(2, 0.75), facecolor='#337ab7')
plot.axes.get_yaxis().set_visible(False)
plot.set_axis_bgcolor("w")
xticks = plot.xaxis.get_major_ticks()
for tick in xticks[1:-1]:
tick.set_visible(False)
tick.label.set_visible(False)
for tick in (xticks[0], xticks[-1]):
tick.label.set_fontsize(8)
plot.figure.subplots_adjust(left=0.15, right=0.85, top=1, bottom=0.35, wspace=0, hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
result_string = 'data:image/png;base64,' + quote(base64.b64encode(imgdata.getvalue()))
plt.close(plot.figure)
return result_string
def describe_date_1d(series, base_stats):
stats = {'min': series.min(), 'max': series.max()}
stats['range'] = stats['max'] - stats['min']
stats['type'] = "DATE"
# TODO: Matplotlib can't do dates of histograms.
# stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def describe_categorical_1d(data):
# Only run if at least 1 non-missing value
objcounts = data.value_counts()
top, freq = objcounts.index[0], objcounts.iloc[0]
names = []
result = []
if data.dtype == object or com.is_categorical_dtype(data.dtype):
names += ['top', 'freq', 'type']
result += [top, freq, 'CAT']
return pd.Series(result, index=names, name=data.name)
def describe_constant_1d(data):
return pd.Series(['CONST'], index=['type'], name=data.name)
def describe_unique_1d(data):
return pd.Series(['UNIQUE'], index=['type'], name=data.name)
def describe_1d(data):
# Is unique
# Percent missing
names = ['count', 'distinct_count', 'p_missing', 'n_missing', 'is_unique', 'mode', 'p_unique', 'memorysize']
count = data.count()
leng = len(data)
distinct_count = data.nunique(dropna=False)
if count > distinct_count > 1:
mode = data.mode().iloc[0]
else:
mode = data[0]
results_data = [count, distinct_count, 1 - count / leng, leng - count, distinct_count == leng, mode,
distinct_count / count, data.memory_usage()]
result = pd.Series(results_data, index=names, name=data.name)
if distinct_count <= 1:
result = result.append(describe_constant_1d(data))
elif com.is_numeric_dtype(data):
result = result.append(describe_numeric_1d(data, result))
elif com.is_datetime64_dtype(data):
result = result.append(describe_date_1d(data, result))
elif distinct_count == leng:
result = result.append(describe_unique_1d(data))
else:
result = result.append(describe_categorical_1d(data))
return result
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
ldesc = [describe_1d(s) for _, s in df.iteritems()]
# set a convenient order for rows
names = []
ldesc_indexes = sorted([x.index for x in ldesc], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
table_stats = {'n': len(df), 'nvar': len(df.columns)}
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (table_stats['n'] * table_stats['nvar'])
table_stats['n_duplicates'] = sum(df.duplicated())
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize / table_stats['n'])
table_stats.update({k: 0 for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE")})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
return {'table': table_stats, 'variables': variable_stats.T, 'freq': {k: df[k].value_counts() for k in df.columns}}
def describe(df, bins=10, check_correlation=True, correlation_overrides=None, pool_size=multiprocessing.cpu_count(), **kwargs):
"""Generates a dict containing summary statistics for a given dataset stored as a pandas `DataFrame`.
Used has is it will output its content as an HTML report in a Jupyter notebook.
Parameters
----------
df : DataFrame
Data to be analyzed
bins : int
Number of bins in histogram
check_correlation : boolean
Whether or not to check correlation.
correlation_overrides : list
Variable names not to be rejected because they are correlated
pool_size: int
Number of workers in thread pool
Returns
-------
dict
Containing the following keys:
* table: general statistics on the dataset
* variables: summary statistics for each variable
* freq: frequency table
Notes:
------
* The section dedicated to check the correlation should be externalized
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
try:
# reset matplotlib style before use
# Fails in matplotlib 1.4.x so plot might look bad
matplotlib.style.use("default")
except:
pass
matplotlib.style.use(resource_filename(__name__, "pandas_profiling.mplstyle"))
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
# Describe all variables in a univariate way
pool = multiprocessing.Pool(pool_size)
local_multiprocess_func = partial(multiprocess_func, **kwargs)
ldesc = {col: s for col, s in pool.map(local_multiprocess_func, df.iteritems())}
pool.close()
# Check correlations between variable
if check_correlation is True:
''' TODO: corr(x,y) > 0.9 and corr(y,z) > 0.9 does not imply corr(x,z) > 0.9
If x~y and y~z but not x~z, it would be better to delete only y
Better way would be to find out which variable causes the highest increase in multicollinearity.
'''
corr = df.corr()
for x, corr_x in corr.iterrows():
if correlation_overrides and x in correlation_overrides:
continue
for y, corr in corr_x.iteritems():
if x == y: break
if corr > 0.9:
ldesc[x] = pd.Series(['CORR', y, corr], index=['type', 'correlation_var', 'correlation'])
categorical_variables = [(name, data) for (name, data) in df.iteritems() if base.get_vartype(data)=='CAT']
for (name1, data1), (name2, data2) in itertools.combinations(categorical_variables, 2):
if correlation_overrides and name1 in correlation_overrides:
continue
confusion_matrix=pd.crosstab(data1,data2)
if confusion_matrix.values.diagonal().sum() == len(df):
ldesc[name1] = pd.Series(['RECODED', name2], index=['type', 'correlation_var'])
# Convert ldesc to a DataFrame
names = []
ldesc_indexes = sorted([x.index for x in ldesc.values()], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
# General statistics
table_stats = {'n': len(df), 'nvar': len(df.columns)}
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (table_stats['n'] * table_stats['nvar'])
table_stats['n_duplicates'] = sum(df.duplicated())
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize / table_stats['n'])
table_stats.update({k: 0 for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE", "CORR", "RECODED", "BOOL")})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
table_stats['REJECTED'] = table_stats['CONST'] + table_stats['CORR'] + table_stats['RECODED']
return {'table': table_stats, 'variables': variable_stats.T, 'freq': {k: df[k].value_counts() for k in df.columns}}
def describe(df, bins=10, correlation_overrides=None, pool_size=multiprocessing.cpu_count(), **kwargs):
"""
Generates a object containing summary statistics for a given DataFrame
:param df: DataFrame to be analyzed
:param bins: Number of bins in histogram
:param correlation_overrides: Variable names not to be rejected because they are correlated
:param pool_size: Number of workers in thread pool
:return: Dictionary containing
table: general statistics on the DataFrame
variables: summary statistics for each variable
freq: frequency table
"""
if not isinstance(df, pd.DataFrame):
raise TypeError("df must be of type pandas.DataFrame")
if df.empty:
raise ValueError("df can not be empty")
try:
# reset matplotlib style before use
# Fails in matplotlib 1.4.x so plot might look bad
matplotlib.style.use("default")
except:
pass
matplotlib.style.use(resource_filename(__name__, "pandas_profiling.mplstyle"))
def pretty_name(x):
x *= 100
if x == int(x):
return '%.0f%%' % x
else:
return '%.1f%%' % x
def describe_numeric_1d(series, base_stats):
stats = {'mean': series.mean(), 'std': series.std(), 'variance': series.var(), 'min': series.min(),
'max': series.max()}
stats['range'] = stats['max'] - stats['min']
for x in np.array([0.05, 0.25, 0.5, 0.75, 0.95]):
stats[pretty_name(x)] = series.dropna().quantile(x) # The dropna() is a workaround for https://github.com/pydata/pandas/issues/13098
stats['iqr'] = stats['75%'] - stats['25%']
stats['kurtosis'] = series.kurt()
stats['skewness'] = series.skew()
stats['sum'] = series.sum()
stats['mad'] = series.mad()
stats['cv'] = stats['std'] / stats['mean'] if stats['mean'] else np.NaN
stats['type'] = "NUM"
stats['n_zeros'] = (len(series) - np.count_nonzero(series))
stats['p_zeros'] = stats['n_zeros'] / len(series)
# Histograms
stats['histogram'] = histogram(series)
stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def _plot_histogram(series, figsize=(6, 4), facecolor='#337ab7', bins=bins):
"""Plot an histogram from the data and return the AxesSubplot object.
Parameters
----------
series: Series, default None
The data to plot
figsize: a tuple (width, height) in inches, default (6,4)
The size of the figure.
facecolor: str
The color code.
bins: int, default
The number of equal-width bins in the given range.
Returns
-------
matplotlib.AxesSubplot, The plot.
"""
if com.is_datetime64_dtype(series):
# TODO: These calls should be merged
fig = plt.figure(figsize=figsize)
plot = fig.add_subplot(111)
plot.set_ylabel('Frequency')
try:
plot.hist(series.values, facecolor=facecolor, bins=bins)
except TypeError: # matplotlib 1.4 can't plot dates so will show empty plot instead
pass
else:
plot = series.plot(kind='hist', figsize=figsize,
facecolor=facecolor,
bins=bins) # TODO when running on server, send this off to a different thread
return plot
def histogram(series):
"""Plot an histogram of the data.
Parameters
----------
series: Series, default None
The data to plot.
Returns
-------
str, The resulting image encoded as a string.
"""
imgdata = BytesIO()
plot = _plot_histogram(series)
plot.figure.subplots_adjust(left=0.15, right=0.95, top=0.9, bottom=0.1, wspace=0, hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
result_string = 'data:image/png;base64,' + quote(base64.b64encode(imgdata.getvalue()))
# TODO Think about writing this to disk instead of caching them in strings
plt.close(plot.figure)
return result_string
def mini_histogram(series):
"""Plot a small (mini) histogram of the data.
Parameters
----------
series: Series, default None
The data to plot.
Returns
-------
str, The resulting image encoded as a string.
"""
imgdata = BytesIO()
plot = _plot_histogram(series, figsize=(2, 0.75))
plot.axes.get_yaxis().set_visible(False)
plot.set_axis_bgcolor("w")
xticks = plot.xaxis.get_major_ticks()
for tick in xticks[1:-1]:
tick.set_visible(False)
tick.label.set_visible(False)
for tick in (xticks[0], xticks[-1]):
tick.label.set_fontsize(8)
plot.figure.subplots_adjust(left=0.15, right=0.85, top=1, bottom=0.35, wspace=0, hspace=0)
plot.figure.savefig(imgdata)
imgdata.seek(0)
result_string = 'data:image/png;base64,' + quote(base64.b64encode(imgdata.getvalue()))
plt.close(plot.figure)
return result_string
def describe_date_1d(series, base_stats):
stats = {'min': series.min(), 'max': series.max()}
stats['range'] = stats['max'] - stats['min']
stats['type'] = "DATE"
stats['histogram'] = histogram(series)
stats['mini_histogram'] = mini_histogram(series)
return pd.Series(stats, name=series.name)
def describe_categorical_1d(data):
# Only run if at least 1 non-missing value
objcounts = data.value_counts()
top, freq = objcounts.index[0], objcounts.iloc[0]
names = []
result = []
if data.dtype == object or com.is_categorical_dtype(data.dtype):
names += ['top', 'freq']
result += [top, freq]
return pd.Series(result, index=names, name=data.name)
def describe_constant_1d(data):
return pd.Series(['CONST'], index=['type'], name=data.name)
def describe_unique_1d(data):
return pd.Series(['UNIQUE'], index=['type'], name=data.name)
def describe_1d(data):
leng = len(data) # number of observations in the Series
count = data.count() # number of non-NaN observations in the Series
# Replace infinite values with NaNs to avoid issues with
# histograms later.
data.replace(to_replace=[np.inf, np.NINF, np.PINF], value=np.nan, inplace=True)
n_infinite = count - data.count() # number of infinte observations in the Series
distinct_count = data.nunique(dropna=False) # number of unique elements in the Series
if count > distinct_count > 1:
mode = data.mode().iloc[0]
else:
mode = data[0]
results_data = {'count': count,
'distinct_count': distinct_count,
'p_missing': 1 - count / leng,
'n_missing': leng - count,
'p_infinite': n_infinite / leng,
'n_infinite': n_infinite,
'is_unique': distinct_count == leng,
'mode': mode,
'p_unique': distinct_count / count}
try:
# pandas 0.17 onwards
results_data['memorysize'] = data.memory_usage()
except:
results_data['memorysize'] = 0
result = pd.Series(results_data, name=data.name)
if distinct_count <= 1:
result = result.append(describe_constant_1d(data))
elif com.is_numeric_dtype(data):
result = result.append(describe_numeric_1d(data, result))
elif com.is_datetime64_dtype(data):
result = result.append(describe_date_1d(data, result))
elif distinct_count == leng:
result = result.append(describe_unique_1d(data))
else:
result = result.append(describe_categorical_1d(data))
result['type'] = 'CAT'
return result
if not pd.Index(np.arange(0, len(df))).equals(df.index):
# Treat index as any other column
df = df.reset_index()
# Describe all variables in a univariate way
pool = multiprocessing.Pool(pool_size)
local_multiprocess_func = partial(multiprocess_func, **kwargs)
ldesc = {col: s for col, s in pool.map(local_multiprocess_func, df.iteritems())}
# Check correlations between variables
''' TODO: corr(x,y) > 0.9 and corr(y,z) > 0.9 does not imply corr(x,z) > 0.9
If x~y and y~z but not x~z, it would be better to delete only y
Better way would be to find out which variable causes the highest increase in multicollinearity.
'''
corr = df.corr()
for x, corr_x in corr.iterrows():
if correlation_overrides and x in correlation_overrides:
continue
for y, corr in corr_x.iteritems():
if x == y: break
if corr > 0.9:
ldesc[x] = pd.Series(['CORR', y, corr], index=['type', 'correlation_var', 'correlation'], name=x)
# Convert ldesc to a DataFrame
names = []
ldesc_indexes = sorted([x.index for x in ldesc.values()], key=len)
for idxnames in ldesc_indexes:
for name in idxnames:
if name not in names:
names.append(name)
variable_stats = pd.concat(ldesc, join_axes=pd.Index([names]), axis=1)
variable_stats.columns.names = df.columns.names
# General statistics
table_stats = {'n': len(df), 'nvar': len(df.columns)}
table_stats['total_missing'] = variable_stats.loc['n_missing'].sum() / (table_stats['n'] * table_stats['nvar'])
table_stats['n_duplicates'] = sum(df.duplicated())
memsize = df.memory_usage(index=True).sum()
table_stats['memsize'] = formatters.fmt_bytesize(memsize)
table_stats['recordsize'] = formatters.fmt_bytesize(memsize / table_stats['n'])
table_stats.update({k: 0 for k in ("NUM", "DATE", "CONST", "CAT", "UNIQUE", "CORR")})
table_stats.update(dict(variable_stats.loc['type'].value_counts()))
table_stats['REJECTED'] = table_stats['CONST'] + table_stats['CORR']
return {'table': table_stats, 'variables': variable_stats.T, 'freq': {k: df[k].value_counts() for k in df.columns}}
