CSIT-913: Continuous Trending, Analysis and Change Detection

 - CSIT-915: LLD
 - CSIT-917: Functions to evaluate the results according to the PASS / FAIL criteria
 - CSIT-918: Sphinx configuration
 - CSIT-948: Statistical functions
 - CSIT-949: Data models for trending plots
 - CSIT-950: Code trending plots
 - CSIT-951: Static content
 - CSIT-984: PAL Specification file
 - CSIT-996: Download data from nexus

Change-Id: Icb9305945bb0f142135bb177cb8781ba0096280e
Signed-off-by: Tibor Frank <tifrank@cisco.com>

1 files changed, 108 insertions, 17 deletions

diff --git a/resources/tools/presentation/utils.py b/resources/tools/presentation/utils.py
index 7037404c27..966d7f558b 100644
--- a/resources/tools/presentation/utils.py
+++ b/resources/tools/presentation/utils.py
@@ -14,12 +14,18 @@
 """General purpose utilities.
 """
 
+import subprocess
 import numpy as np
+import pandas as pd
+import logging
 
-from os import walk
-from os.path import join
+from os import walk, makedirs, environ
+from os.path import join, isdir
+from shutil import copy, Error
 from math import sqrt
 
+from errors import PresentationError
+
 
 def mean(items):
     """Calculate mean value from the items.
@@ -62,27 +68,37 @@ def relative_change(nr1, nr2):
     return float(((nr2 - nr1) / nr1) * 100)
 
 
-def remove_outliers(input_data, outlier_const):
-    """
+def find_outliers(input_data, outlier_const=1.5):
+    """Go through the input data and generate two pandas series:
+    - input data without outliers
+    - outliers.
+    The function uses IQR to detect outliers.
 
-    :param input_data: Data from which the outliers will be removed.
+    :param input_data: Data to be examined for outliers.
     :param outlier_const: Outlier constant.
-    :type input_data: list
+    :type input_data: pandas.Series
     :type outlier_const: float
-    :returns: The input list without outliers.
-    :rtype: list
+    :returns: Tuple: input data with outliers removed; Outliers.
+    :rtype: tuple (trimmed_data, outliers)
     """
 
-    data = np.array(input_data)
-    upper_quartile = np.percentile(data, 75)
-    lower_quartile = np.percentile(data, 25)
+    upper_quartile = input_data.quantile(q=0.75)
+    lower_quartile = input_data.quantile(q=0.25)
     iqr = (upper_quartile - lower_quartile) * outlier_const
-    quartile_set = (lower_quartile - iqr, upper_quartile + iqr)
-    result_lst = list()
-    for y in data.tolist():
-        if quartile_set[0] <= y <= quartile_set[1]:
-            result_lst.append(y)
-    return result_lst
+    low = lower_quartile - iqr
+    high = upper_quartile + iqr
+    trimmed_data = pd.Series()
+    outliers = pd.Series()
+    for item in input_data.items():
+        item_pd = pd.Series([item[1], ], index=[item[0], ])
+        if low <= item[1] <= high:
+            trimmed_data = trimmed_data.append(item_pd)
+        else:
+            trimmed_data = trimmed_data.append(pd.Series([np.nan, ],
+                                                         index=[item[0], ]))
+            outliers = outliers.append(item_pd)
+
+    return trimmed_data, outliers
 
 
 def get_files(path, extension=None, full_path=True):
@@ -127,3 +143,78 @@ def get_rst_title_char(level):
         return chars[level]
     else:
         return chars[-1]
+
+
+def execute_command(cmd):
+    """Execute the command in a subprocess and log the stdout and stderr.
+
+    :param cmd: Command to execute.
+    :type cmd: str
+    :returns: Return code of the executed command.
+    :rtype: int
+    """
+
+    env = environ.copy()
+    proc = subprocess.Popen(
+        [cmd],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        shell=True,
+        env=env)
+
+    stdout, stderr = proc.communicate()
+
+    logging.info(stdout)
+    logging.info(stderr)
+
+    if proc.returncode != 0:
+        logging.error("    Command execution failed.")
+    return proc.returncode, stdout, stderr
+
+
+def get_last_build_number(jenkins_url, job_name):
+    """
+
+    :param jenkins_url:
+    :param job_name:
+    :return:
+    """
+
+    url = "{}/{}/lastSuccessfulBuild/buildNumber".format(jenkins_url, job_name)
+    cmd = "wget -qO- {url}".format(url=url)
+
+    return execute_command(cmd)
+
+
+def archive_input_data(spec):
+    """Archive the report.
+
+    :param spec: Specification read from the specification file.
+    :type spec: Specification
+    :raises PresentationError: If it is not possible to archive the input data.
+    """
+
+    logging.info("    Archiving the input data files ...")
+
+    if spec.is_debug:
+        extension = spec.debug["input-format"]
+    else:
+        extension = spec.input["file-format"]
+    data_files = get_files(spec.environment["paths"]["DIR[WORKING,DATA]"],
+                           extension=extension)
+    dst = spec.environment["paths"]["DIR[STATIC,ARCH]"]
+    logging.info("      Destination: {0}".format(dst))
+
+    try:
+        if not isdir(dst):
+            makedirs(dst)
+
+        for data_file in data_files:
+            logging.info("      Copying the file: {0} ...".format(data_file))
+            copy(data_file, dst)
+
+    except (Error, OSError) as err:
+        raise PresentationError("Not possible to archive the input data.",
+                                str(err))
+
+    logging.info("    Done.")