def to_image(self, path):
"""
Save the profiler result as image
:param self:
:param path:
:return:
"""
path_css = os.path.dirname(os.path.abspath(__file__))
css = path_css + "//..//css//styles.css"
imgkit.from_string(self.html, path, css=css)
print_html("<img src='" + path + "'>")
def table_image(self, path, limit=10):
"""
:param self:
:param limit:
:param path:
:return:
"""
# imgkit.from_url('http://google.com', 'out.jpg')
path_css = os.path.dirname(os.path.abspath(__file__))
css = path_css + "//..//css//styles.css"
imgkit.from_string(self.table_html(limit=limit, full=True), path, css=css)
print_html("<img src='" + path + "'>")
def _load_css():
"""
Try to load the css for templates
:return:
"""
try:
if __IPYTHON__:
path = os.path.dirname(os.path.abspath(__file__))
url = path + "//css//styles.css"
styles = open(url, "r", encoding="utf8").read()
s = '<style>%s</style>' % styles
print_html(s)
except NameError:
pass
def table(self, limit=100, columns=None):
try:
__IPYTHON__
result = self.table_html(limit=limit, columns=columns)
return print_html(result)
except NameError:
self.show()
def table(self, limit=100, columns=None, title=None):
try:
if __IPYTHON__ and DataFrame.output is "html":
result = self.table_html(title=title, limit=limit, columns=columns)
return print_html(result)
else:
self.show()
except NameError:
self.show()
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