def hist(columns=None, buckets=10):
"""
Plot histogram
:param columns: Columns to be printed
:param buckets: Number of buckets
:return:
"""
columns = parse_columns(self, columns, filter_by_column_dtypes=PYSPARK_NUMERIC_TYPES)
for col_name in columns:
data = self.cols.hist(col_name, buckets)
plot_hist({col_name: data}, output="image")
def hist(columns=None, buckets=10):
"""
Plot histogram
:param columns: Columns to be printed
:param buckets: Number of buckets
:return:
"""
columns = parse_columns(self, columns)
for col_name in columns:
data = self.cols.hist(col_name, buckets)
plot_hist({col_name: data}, output="image")
def hist(columns=None, buckets=10, output=None, path=None):
"""
Plot histogram
:param columns: Columns to be printed
:param buckets: Number of buckets
:param output:
:param path:
:return:
"""
columns = parse_columns(self,
columns,
filter_by_column_dtypes=PYSPARK_NUMERIC_TYPES)
check_column_numbers(columns, "*")
for col_name in columns:
data = self.cols.hist(col_name, buckets)
plot_hist({col_name: data}, output=output, path=path)
def run(self, df, columns, buckets=20):
"""
Return statistical information in HTML Format
:param df:
:param columns:
:param buckets:
:return:
"""
columns = parse_columns(df, columns)
output = Profiler.to_json(df, columns, buckets)
# Load jinja
path = os.path.dirname(os.path.abspath(__file__))
template_loader = jinja2.FileSystemLoader(searchpath=path +
"//templates")
template_env = jinja2.Environment(loader=template_loader,
autoescape=True)
# Render template
# Create the profiler info header
html = ""
general_template = template_env.get_template("general_info.html")
html = html + general_template.render(data=output)
template = template_env.get_template("one_column.html")
# Create every column stats
for col_name in columns:
if "hist" in output["columns"][col_name]:
hist_pic = plot_hist(
{col_name: output["columns"][col_name]["hist"]},
output="base64")
else:
hist_pic = None
if "frequency" in output["columns"][col_name]:
freq_pic = plot_freq(
{col_name: output["columns"][col_name]["frequency"]},
output="base64")
else:
freq_pic = None
html = html + template.render(data=output["columns"][col_name],
hist_pic=hist_pic,
freq_pic=freq_pic)
html = html + df.table_html(10)
# df.plots.correlation(columns)
# Display HTML
display(HTML(html))
# Save to file
write_json(output, self.path)
def run(self, df, columns, buckets=40, infer=False, relative_error=1):
"""
Return dataframe statistical information in HTML Format
:param df: Dataframe to be analyzed
:param columns: Columns to be analized
:param buckets: Number of buckets calculated to print the histogram
:param infer: infer data type
:param relative_error: Relative Error for quantile discretizer calculation
:return:
"""
columns = parse_columns(df, columns)
output = Profiler.to_json(df, columns, buckets, infer, relative_error)
# Load jinja
path = os.path.dirname(os.path.abspath(__file__))
template_loader = jinja2.FileSystemLoader(searchpath=path +
"//templates")
template_env = jinja2.Environment(loader=template_loader,
autoescape=True)
# Render template
# Create the profiler info header
html = ""
general_template = template_env.get_template("general_info.html")
html = html + general_template.render(data=output)
template = template_env.get_template("one_column.html")
# Create every column stats
for col_name in columns:
hist_pic = None
col = output["columns"][col_name]
if "hist" in col:
if col["column_dtype"] == "date":
hist_year = plot_hist({col_name: col["hist"]["years"]},
"base64", "years")
hist_month = plot_hist({col_name: col["hist"]["months"]},
"base64", "months")
hist_weekday = plot_hist(
{col_name: col["hist"]["weekdays"]}, "base64",
"weekdays")
hist_hour = plot_hist({col_name: col["hist"]["hours"]},
"base64", "hours")
hist_minute = plot_hist({col_name: col["hist"]["minutes"]},
"base64", "minutes")
hist_pic = {
"hist_years": hist_year,
"hist_months": hist_month,
"hist_weekdays": hist_weekday,
"hist_hours": hist_hour,
"hist_minutes": hist_minute
}
else:
hist = plot_hist({col_name: col["hist"]}, output="base64")
hist_pic = {"hist_pic": hist}
if "frequency" in col:
freq_pic = plot_freq({col_name: col["frequency"]},
output="base64")
else:
freq_pic = None
html = html + template.render(
data=col, freq_pic=freq_pic, **hist_pic)
html = html + df.table_html(10)
# Display HTML
print_html(html)
# send to queue
if self.queue_url is not None:
self.to_queue(output)
# JSON
# Save in case we want to output to a json file
self.json = output
# Save file in json format
write_json(output, self.path)
# Save in case we want to output to a html file
self.html = html
