[Feature] Graphing tool CLI update

Added CLI integration for graphing tool.
Added area graphing features for graphing tool.
Added PDF output for graphing tool.
Added probe graph output for graphing tool.

3 files changed, 275 insertions, 115 deletions

diff --git a/tools/graphing.py b/tools/graphing.py
index d2ea0c1..5ba3fbf 100644
--- a/tools/graphing.py
+++ b/tools/graphing.py
@@ -2,9 +2,19 @@ import re
 
 import pandas as pd
 import matplotlib.pyplot as plt
+import matplotlib.backends.backend_pdf # For pdf output
 import os
+import argparse
+import pprint
 
-__FILENAMES__ = {
+parser = argparse.ArgumentParser(description='Make some graphs using CSV files!')
+# parser.add_argument("filename", type=argparse.FileType('r'))
+parser.add_argument("filename", type=str, help="Put a single one of the log files from a set here, " +
+                                               "and it will parse the rest")
+
+
+# Regex should be described below in match_filename(filename, component)
+__COMPONENTS__ = {
     "foreign": "-foreign-",
     "self": "-self-",
     "download": "-throughput-download-",
@@ -12,6 +22,27 @@ __FILENAMES__ = {
     "granular": "-throughput-granular-",
 }
 
+__LINECOLOR__ = {
+    "download": "#0095ed",
+    "upload": "#44BB66",
+    "foreign": "#ac7ae7", # "#7522d7",
+    "selfUp": "#7ccf93",
+    "selfDown": "#4cb4f2" # "#7fcaf6",
+}
+
+
+def match_filename(filename, component):
+    """
+    Input a filename and a component regex component to match the filename to its <start><component><end> regex.
+    Returns a match object with groups: start, component, end.
+
+    :param filename: String of filename
+    :param component: String to add into the regex
+    :return: Match object or None
+    """
+    regex = f"(?P<start>.*)(?P<component>{component})(?P<end>.*)"
+    return re.match(regex, filename)
+
 
 def seconds_since_start(dfs, start, column_name="SecondsSinceStart"):
     """
@@ -24,7 +55,7 @@ def seconds_since_start(dfs, start, column_name="SecondsSinceStart"):
     :return: Inplace addition of column using passed column name
     """
     for df in dfs:
-        df[column_name] = (df["CreationTime"]-start).apply(pd.Timedelta.total_seconds)
+        df[column_name] = (df["CreationTime"] - start).apply(pd.Timedelta.total_seconds)
 
 
 def find_earliest(dfs):
@@ -42,15 +73,19 @@ def find_earliest(dfs):
     return earliest
 
 
-def timeSinceStart(dfs, start):
+def time_since_start(dfs, start, column_name="TimeSinceStart"):
     """
-    Adds "TimeSinceStart" column to all dataframes
-    :param dfs:
-    :param start:
-    :return:
+    Adds "Seconds Since Start" column to all DataFrames in List of DataFrames,
+    based on "CreationTime" column within them and start time passed.
+
+    :param dfs: List of DataFrames. Each DataFrame MUST contain DateTime column named "CreationTime"
+    :param start: DateTime start time
+    :param column_name: String of column name to add, default "SecondsSinceStart"
+    :return: Inplace addition of column using passed column name
     """
     for df in dfs:
-        df["TimeSinceStart"] = df["CreationTime"]-start
+        df[column_name] = df["CreationTime"] - start
+
 
 def probeClean(df):
     # ConnRTT and ConnCongestionWindow refer to Underlying Connection
@@ -118,96 +153,60 @@ def main(title, paths):
 
 
     # Moving Average
-    foreign["DurationMA5"] = foreign["ADJ_Duration"].rolling(window=5).mean()
-    selfUp["DurationMA5"] = selfUp["ADJ_Duration"].rolling(window=5).mean()
-    selfDown["DurationMA5"] = selfDown["ADJ_Duration"].rolling(window=5).mean()
+    foreign["DurationMA10"] = foreign["ADJ_Duration"].rolling(window=10).mean()
+    selfUp["DurationMA10"] = selfUp["ADJ_Duration"].rolling(window=10).mean()
+    selfDown["DurationMA10"] = selfDown["ADJ_Duration"].rolling(window=10).mean()
 
     # Normalize
     dfs = [foreign, selfUp, selfDown, download, upload, granularUp, granularDown]
-    timeSinceStart(dfs, find_earliest(dfs))
+    time_since_start(dfs, find_earliest(dfs))
     seconds_since_start(dfs, find_earliest(dfs))
 
     yCol = "SecondsSinceStart"
 
-    def GraphNormal():
-        ########## Graphing Complete
-        fig, ax = plt.subplots()
-        ax.set_title(title)
-        ax.plot(foreign[yCol], foreign["ADJ_Duration"], "b.", label="foreign")
-        ax.plot(selfUp[yCol], selfUp["ADJ_Duration"], "r.", label="selfUP")
-        ax.plot(selfDown[yCol], selfDown["ADJ_Duration"], "c.", label="selfDOWN")
-        ax.plot(foreign[yCol], foreign["DurationMA5"], "b--", label="foreignMA")
-        ax.plot(selfUp[yCol], selfUp["DurationMA5"], "r--", label="selfUPMA")
-        ax.plot(selfDown[yCol], selfDown["DurationMA5"], "c--", label="selfDOWNMA")
-        ax.set_ylim([0, max(foreign["ADJ_Duration"].max(), self["ADJ_Duration"].max())])
-        ax.legend(loc="upper left")
-
-        secax = ax.twinx()
-        secax.plot(download[yCol], download["ADJ_Throughput"], "g-", label="download (MB/s)")
-        secax.plot(granularDown[granularDown["ID"] == 0][yCol], granularDown[granularDown["ID"] == 0]["ADJ_Throughput"], "g--", label="Download Connection 0 (MB/S)")
-        secax.plot(upload[yCol], upload["ADJ_Throughput"], "y-", label="upload (MB/s)")
-        secax.plot(granularUp[granularUp["ID"] == 0][yCol], granularUp[granularUp["ID"] == 0]["ADJ_Throughput"], "y--", label="Upload Connection 0 (MB/S)")
-        secax.legend(loc="upper right")
-    #GraphNormal()
-
-    def StackedThroughput():
-        ########## Graphing Stacked
-        fig, ax = plt.subplots()
-        ax.set_title(title + " Granular Throughput")
-        # ax.plot(foreign[yCol], foreign["ADJ_Duration"], "b.", label="foreign")
-        # ax.plot(selfUp[yCol], selfUp["ADJ_Duration"], "r.", label="selfUP")
-        # ax.plot(selfDown[yCol], selfDown["ADJ_Duration"], "c.", label="selfDOWN")
-        # ax.plot(foreign[yCol], foreign["DurationMA5"], "b--", label="foreignMA")
-        # ax.plot(selfUp[yCol], selfUp["DurationMA5"], "r--", label="selfUPMA")
-        # ax.plot(selfDown[yCol], selfDown["DurationMA5"], "c--", label="selfDOWNMA")
-        # ax.set_ylim([0, max(foreign["ADJ_Duration"].max(), self["ADJ_Duration"].max())])
-        # ax.legend(loc="upper left")
-
-        secax = ax.twinx()
-        secax.plot(download[yCol], download["ADJ_Throughput"], "g-", label="download (MB/s)")
-        secax.plot(upload[yCol], upload["ADJ_Throughput"], "y-", label="upload (MB/s)")
-
-        granularDown["bucket"] = granularDown["SecondsSinceStart"].round(0)
-        buckets = pd.DataFrame(granularDown["bucket"].unique())
-        buckets.columns = ["bucket"]
-        buckets = buckets.set_index("bucket")
-        buckets["SecondsSinceStart"] = granularDown.drop_duplicates(subset=["bucket"]).reset_index()["SecondsSinceStart"]
-        buckets["bottom"] = 0
-        for id in sorted(granularDown["ID"].unique()):
-            secax.bar(granularDown[yCol][granularDown["ID"] == id] + .05,
-                      granularDown["ADJ_Throughput"][granularDown["ID"] == id],
-                      width=.09, bottom=buckets.iloc[len(buckets) - len(granularDown[granularDown["ID"] == id]):]["bottom"]
-                      )
-            # ,label=f"Download Connection {id}")
-            buckets["toadd_bottom"] = (granularDown[granularDown["ID"] == id]).set_index("bucket")["ADJ_Throughput"]
-            buckets["toadd_bottom"] = buckets["toadd_bottom"].fillna(0)
-            buckets["bottom"] += buckets["toadd_bottom"]
-
-
-        granularUp["bucket"] = granularUp["SecondsSinceStart"].round(0)
-        buckets = pd.DataFrame(granularUp["bucket"].unique())
-        buckets.columns = ["bucket"]
-        buckets = buckets.set_index("bucket")
-        buckets["SecondsSinceStart"] = granularUp.drop_duplicates(subset=["bucket"]).reset_index()["SecondsSinceStart"]
-        buckets["bottom"] = 0
-        for id in sorted(granularUp["ID"].unique()):
-            secax.bar(granularUp[yCol][granularUp["ID"] == id] - .05, granularUp["ADJ_Throughput"][granularUp["ID"] == id],
-                      width=.09, bottom=buckets.iloc[len(buckets) - len(granularUp[granularUp["ID"] == id]):]["bottom"]
-                      )
-                      #,label=f"Upload Connection {id}")
-            buckets["toadd_bottom"] = (granularUp[granularUp["ID"] == id]).set_index("bucket")["ADJ_Throughput"]
-            buckets["toadd_bottom"] = buckets["toadd_bottom"].fillna(0)
-            buckets["bottom"] += buckets["toadd_bottom"]
-        secax.legend(loc="upper right")
-
-
-        secax.legend(loc="upper left")
+    # stacked_bar_throughput(upload, granularUp, "SecondsSinceStart", "ADJ_Throughput", title + " Upload Stacked",
+    #                       "Upload Throughput MB/s")
+    # stacked_bar_throughput(download, granularDown, "SecondsSinceStart", "ADJ_Throughput", title + " Download Stacked",
+    #                       "Download Throughput MB/s")
+    dfs_dict = {
+        "foreign": foreign,
+        "self": self,
+        "download": download,
+        "upload": upload,
+        "granular": granular,
+        "selfUp": selfUp,
+        "selfDown": selfDown,
+        "granularUp": granularUp,
+        "granularDown": granularDown
+    }
+    fig, ax = plt.subplots()
+    fig.canvas.manager.set_window_title(title + " Standard")
+    graph_normal(dfs_dict, "SecondsSinceStart", ax, title + " Standard")
 
-    #StackedThroughput()
-    stacked_bar_throughput(upload, granularUp, "SecondsSinceStart", "ADJ_Throughput", title + " Upload Stacked",
-                           "Upload Throughput MB/s")
-    stacked_bar_throughput(download, granularDown, "SecondsSinceStart", "ADJ_Throughput", title + " Download Stacked",
-                           "Download Throughput MB/s")
+    fig, ax = plt.subplots()
+    fig.canvas.manager.set_window_title(title + " Standard ms")
+    graph_normal_ms(dfs_dict, "SecondsSinceStart", ax, title + " Standard ms")
+    
+    # Both Upload/Download Granular on one figure
+    fig, axs = plt.subplots(2, 1)
+    fig.canvas.manager.set_window_title(title + " Combined Throughput")
+    stacked_area_throughput(download, granularDown, "SecondsSinceStart", "ADJ_Throughput", axs[0],
+                            title + " Download Stacked",
+                            "Download Throughput MB/s", __LINECOLOR__["download"])
+    stacked_area_throughput(upload, granularUp, "SecondsSinceStart", "ADJ_Throughput", axs[1],
+                            title + " Upload Stacked",
+                            "Upload Throughput MB/s",  __LINECOLOR__["upload"])
+    # Individual figure
+    fig, ax = plt.subplots()
+    fig.canvas.manager.set_window_title(title + " Download Throughput")
+    stacked_area_throughput(download, granularDown, "SecondsSinceStart", "ADJ_Throughput", ax,
+                            title + " Download Stacked",
+                            "Download Throughput MB/s",  __LINECOLOR__["download"])
+    fig, ax = plt.subplots()
+    fig.canvas.manager.set_window_title(title + " Upload Throughput")
+    stacked_area_throughput(upload, granularUp, "SecondsSinceStart", "ADJ_Throughput", ax,
+                            title + " Upload Stacked",
+                            "Upload Throughput MB/s",  __LINECOLOR__["upload"])
 
     def Percent90():
         ######### Graphing Removing 90th Percentile
@@ -244,51 +243,142 @@ def main(title, paths):
                    label="Upload Connection 0 (MB/S)")
         secax.legend(loc="upper right")
 
-    Percent90()
+    # Percent90()
 
-def stacked_bar_throughput(df, granular, xcolumn, ycolumn, title, label):
-    fig, ax = plt.subplots()
+
+def graph_normal_ms(dfs, xcolumn, ax, title):
     ax.set_title(title)
+    ax.set_xlabel("Seconds Since Start (s)")
+
+    # To plot points
+    # ax.plot(dfs["foreign"][xcolumn], dfs["foreign"]["ADJ_Duration"], "b.", label="foreign")
+    # ax.plot(dfs["selfUp"][xcolumn], dfs["selfUp"]["ADJ_Duration"], "r.", label="selfUP")
+    # ax.plot(dfs["selfDown"][xcolumn], dfs["selfDown"]["ADJ_Duration"], "c.", label="selfDOWN")
+    dfs["foreign"]["DurationMA10ms"] = dfs["foreign"]["ADJ_Duration"].rolling(window=10, step=10).mean() * 1000
+    dfs["selfUp"]["DurationMA10ms"] = dfs["selfUp"]["ADJ_Duration"].rolling(window=10, step=10).mean() * 1000
+    dfs["selfDown"]["DurationMA10ms"] = dfs["selfDown"]["ADJ_Duration"].rolling(window=10, step=10).mean() * 1000
+    # Plot lines
+    ax.plot(dfs["foreign"][xcolumn][dfs["foreign"]["DurationMA10ms"].notnull()], dfs["foreign"]["DurationMA10ms"][dfs["foreign"]["DurationMA10ms"].notnull()], "--", linewidth=2, color=__LINECOLOR__["foreign"], label="foreignMA10 (ms)")
+    ax.plot(dfs["selfUp"][xcolumn][dfs["selfUp"]["DurationMA10ms"].notnull()], dfs["selfUp"]["DurationMA10ms"][dfs["selfUp"]["DurationMA10ms"].notnull()], "--", linewidth=2, color=__LINECOLOR__["selfUp"], label="selfUpMA10 (ms)")
+    ax.plot(dfs["selfDown"][xcolumn][dfs["selfDown"]["DurationMA10ms"].notnull()], dfs["selfDown"]["DurationMA10ms"][dfs["selfDown"]["DurationMA10ms"].notnull()], "--", linewidth=2, color=__LINECOLOR__["selfDown"], label="selfDownMA10 (ms)")
+    ax.set_ylim([0, max(dfs["foreign"]["DurationMA10ms"].max(), dfs["selfUp"]["DurationMA10ms"].max(), dfs["selfDown"]["DurationMA10ms"].max()) * 1.01])
+    ax.set_ylabel("RTT (ms)")
+    ax.legend(loc="upper left", title="Probes")
+
 
     secax = ax.twinx()
-    ax.get_yaxis().set_visible(False)
+    secax.plot(dfs["download"][xcolumn], dfs["download"]["ADJ_Throughput"], "-", linewidth=2, color=__LINECOLOR__["download"], label="download (MB/s)")
+    # secax.plot(dfs.granularDown[dfs.granularDown["ID"] == 0][xcolumn], dfs.granularDown[dfs.granularDown["ID"] == 0]["ADJ_Throughput"],
+    #            "g--", label="Download Connection 0 (MB/S)")
+    secax.plot(dfs["upload"][xcolumn], dfs["upload"]["ADJ_Throughput"], "-", linewidth=2, color=__LINECOLOR__["upload"], label="upload (MB/s)")
+    # secax.plot(dfs.granularUp[dfs.granularUp["ID"] == 0][xcolumn], dfs.granularUp[dfs.granularUp["ID"] == 0]["ADJ_Throughput"], "y--",
+    #            label="Upload Connection 0 (MB/S)")
+    secax.set_ylabel("Throughput (MB/s)")
+    secax.legend(loc="upper right")
+
+
+def graph_normal(dfs, xcolumn, ax, title):
+    ax.set_title(title)
     ax.set_xlabel("Seconds Since Start (s)")
+
+    # To plot points
+    # ax.plot(dfs["foreign"][xcolumn], dfs["foreign"]["ADJ_Duration"], "b.", label="foreign")
+    # ax.plot(dfs["selfUp"][xcolumn], dfs["selfUp"]["ADJ_Duration"], "r.", label="selfUP")
+    # ax.plot(dfs["selfDown"][xcolumn], dfs["selfDown"]["ADJ_Duration"], "c.", label="selfDOWN")
+    # Plot lines
+    ax.plot(dfs["foreign"][xcolumn], dfs["foreign"]["DurationMA10"], "--", linewidth=2, color=__LINECOLOR__["foreign"], label="foreignMA10 (s)")
+    ax.plot(dfs["selfUp"][xcolumn], dfs["selfUp"]["DurationMA10"], "--", linewidth=2, color=__LINECOLOR__["selfUp"], label="selfUpMA10 (s)")
+    ax.plot(dfs["selfDown"][xcolumn], dfs["selfDown"]["DurationMA10"], "--", linewidth=2, color=__LINECOLOR__["selfDown"], label="selfDownMA10 (s)")
+    ax.set_ylim([0, max(dfs["foreign"]["DurationMA10"].max(), dfs["selfUp"]["DurationMA10"].max(), dfs["selfDown"]["DurationMA10"].max()) * 1.01])
+    ax.set_ylabel("RTT (s)")
+    ax.legend(loc="upper left", title="Probes")
+
+
+    secax = ax.twinx()
+    secax.plot(dfs["download"][xcolumn], dfs["download"]["ADJ_Throughput"], "-", linewidth=2, color=__LINECOLOR__["download"], label="download (MB/s)")
+    # secax.plot(dfs.granularDown[dfs.granularDown["ID"] == 0][xcolumn], dfs.granularDown[dfs.granularDown["ID"] == 0]["ADJ_Throughput"],
+    #            "g--", label="Download Connection 0 (MB/S)")
+    secax.plot(dfs["upload"][xcolumn], dfs["upload"]["ADJ_Throughput"], "-", linewidth=2, color=__LINECOLOR__["upload"], label="upload (MB/s)")
+    # secax.plot(dfs.granularUp[dfs.granularUp["ID"] == 0][xcolumn], dfs.granularUp[dfs.granularUp["ID"] == 0]["ADJ_Throughput"], "y--",
+    #            label="Upload Connection 0 (MB/S)")
     secax.set_ylabel("Throughput (MB/s)")
-    # secax.set_xticks(range(0, round(granular[xcolumn].max()) + 1)) # Ticks every 1 second
+    secax.legend(loc="upper right")
+    
+
+def stacked_area_throughput(throughput_df, granular, xcolumn, ycolumn, ax, title, label, linecolor="black"):
+    ax.set_title(title)
+
+    ax.yaxis.tick_right()
+    ax.yaxis.set_label_position("right")
+    ax.set_xlabel("Seconds Since Start (s)")
+    ax.set_ylabel("Throughput (MB/s)")
+    # ax.set_xticks(range(0, round(granular[xcolumn].max()) + 1)) # Ticks every 1 second
 
     # Plot Main Throughput
-    secax.plot(df[xcolumn], df[ycolumn], "k--", label=label)
+    ax.plot(throughput_df[xcolumn], throughput_df[ycolumn], "-", color="white", linewidth=3)
+    ax.plot(throughput_df[xcolumn], throughput_df[ycolumn], "-", color=linecolor, linewidth=2, label=label)
 
     df_gran = granular.copy()
+
+    # df_gran["bucket"] = df_gran[xcolumn].round(0) # With rounding
+    df_gran["bucket"] = df_gran[xcolumn]  # Without rounding (csv creation time points need to be aligned)
+    df_gran = df_gran.set_index(xcolumn)
+
+    buckets = pd.DataFrame(df_gran["bucket"].unique())
+    buckets.columns = ["bucket"]
+    buckets = buckets.set_index("bucket")
+    for id in sorted(df_gran["ID"].unique()):
+        buckets[id] = df_gran[ycolumn][df_gran["ID"] == id]
+    buckets = buckets.fillna(0)
+
+    # Plot Stacked Area Throughput
+    ax.stackplot(buckets.index, buckets.transpose())
+    ax.legend(loc="upper right")
+
+
+def stacked_bar_throughput(throughput_df, granular, xcolumn, ycolumn, ax, title, label, linecolor="black"):
+    ax.set_title(title)
+
+    ax.yaxis.tick_right()
+    ax.yaxis.set_label_position("right")
+    ax.set_xlabel("Seconds Since Start (s)")
+    ax.set_ylabel("Throughput (MB/s)")
+    # ax.set_xticks(range(0, round(granular[xcolumn].max()) + 1)) # Ticks every 1 second
+
+    # Plot Main Throughput
+    ax.plot(throughput_df[xcolumn], throughput_df[ycolumn], "-", color=linecolor, label=label)
+
+    df_gran = granular.copy()
+
     # df_gran["bucket"] = df_gran[xcolumn].round(0) # With rounding
     df_gran["bucket"] = df_gran[xcolumn] # Without rounding (csv creation time points need to be aligned)
+
     buckets = pd.DataFrame(df_gran["bucket"].unique())
     buckets.columns = ["bucket"]
     buckets = buckets.set_index("bucket")
     buckets[xcolumn] = df_gran.drop_duplicates(subset=["bucket"]).reset_index()[xcolumn]
     buckets["bottom"] = 0
     for id in sorted(df_gran["ID"].unique()):
-        secax.bar(df_gran[xcolumn][df_gran["ID"] == id],
-                  df_gran[ycolumn][df_gran["ID"] == id],
-                  width=.25, bottom=buckets.iloc[len(buckets) - len(df_gran[df_gran["ID"] == id]):]["bottom"]
-                  )
+        ax.bar(df_gran[xcolumn][df_gran["ID"] == id],
+               df_gran[ycolumn][df_gran["ID"] == id],
+               width=.1, bottom=buckets.iloc[len(buckets) - len(df_gran[df_gran["ID"] == id]):]["bottom"]
+               )
         # ,label=f"Download Connection {id}")
         buckets["toadd_bottom"] = (df_gran[df_gran["ID"] == id]).set_index("bucket")[ycolumn]
         buckets["toadd_bottom"] = buckets["toadd_bottom"].fillna(0)
         buckets["bottom"] += buckets["toadd_bottom"]
 
-    secax.legend(loc="upper right")
+    ax.legend(loc="upper right")
 
 
-def findFiles(dir):
+def find_files(directory):
     matches = {}
 
-    files = os.listdir(dir)
+    files = os.listdir(directory)
     for file in files:
-        if os.path.isfile(dir+file):
-            for name in __FILENAMES__:
-                regex = "(?P<start>.*)(?P<type>" + __FILENAMES__[name] + ")(?P<end>.*)"
-                match = re.match(regex, file)
+        if os.path.isfile(directory + file):
+            for name in __COMPONENTS__:
+                match = match_filename(file, __COMPONENTS__[name])
                 if match is not None:
                     start = match.group("start")
                     end = match.group("end")
@@ -298,10 +388,43 @@ def findFiles(dir):
                         matches[start][end] = {}
                     if name in matches[start][end]:
                         print("ERROR ALREADY FOUND A FILE THAT HAS THE SAME MATCHING")
-                    matches[start][end][name] = dir+file
+                    matches[start][end][name] = directory + file
+    return matches
+
+
+def find_matching_files(directory, filename):
+    matches = {}
+
+    # First determine the file's structure
+    match = match_filename(os.path.basename(filename), "|".join(__COMPONENTS__.values()))
+    if match is not None:
+        file_start = match.group("start")
+        file_end = match.group("end")
+    else:
+        print(f"ERROR COULD NOT MATCH FILE TO KNOWN SCHEMA: {filename}")
+        return matches
+
+    # Find its other matching files
+    files = os.listdir(directory)
+    for file in files:
+        if os.path.isfile(directory + file):
+            for name in __COMPONENTS__:
+                match = match_filename(file, __COMPONENTS__[name])
+                if match is not None:
+                    start = match.group("start")
+                    end = match.group("end")
+                    if file_start == start and file_end == end:
+                        if start not in matches:
+                            matches[start] = {}
+                        if end not in matches[start]:
+                            matches[start][end] = {}
+                        if name in matches[start][end]:
+                            print("ERROR ALREADY FOUND A FILE THAT HAS THE SAME MATCHING")
+                        matches[start][end][name] = directory + file
     return matches
 
-def generatePaths():
+
+def generate_paths():
     return {
         "foreign": "",
         "self": "",
@@ -310,13 +433,15 @@ def generatePaths():
         "granular": "",
     }
 
-def makeGraphs(files):
+
+def make_graphs(files, save):
+    num_fig = 1
     for start in files:
         x = 0
         for end in files[start]:
             # Check if it contains all file fields
             containsALL = True
-            for key in __FILENAMES__:
+            for key in __COMPONENTS__:
                 if key not in files[start][end]:
                     containsALL = False
             # If we don't have all files then loop to next one
@@ -324,14 +449,35 @@ def makeGraphs(files):
                 continue
 
             main(start + " - " + str(x), files[start][end])
+            if save:
+                pdf = matplotlib.backends.backend_pdf.PdfPages(f"{start} - {x}.pdf")
+                for fig in range(num_fig, plt.gcf().number + 1):
+                    plt.figure(fig).set(size_inches=(11, 6.1875))  # 16:9 ratio for screens (11 x 6.1875) # 11 x 8.5 for page size
+                    plt.figure(fig).tight_layout()
+                    pdf.savefig(fig)
+                    plt.figure(fig).set(size_inches=(10, 6.6))
+                    plt.figure(fig).tight_layout()
+                pdf.close()
+                num_fig = plt.gcf().number + 1
             x += 1
 
+
 # Press the green button in the gutter to run the script.
 if __name__ == '__main__':
-    paths = generatePaths()
+    ARGS = parser.parse_args()
+    paths = generate_paths()
 
-    files = findFiles("./Data/WillTest/")
-    print(files)
-    makeGraphs(files)
+    print(f"Looking for files in directory: {os.path.dirname(ARGS.filename)}")
+    # files = find_files(os.path.dirname(ARGS.filename) + "/")
+    if os.path.isfile(ARGS.filename):
+        files = find_matching_files(os.path.dirname(ARGS.filename) + "/", ARGS.filename)
+    elif os.path.isdir(ARGS.filename):
+        files = find_files(ARGS.filename)
+    else:
+        print("Error: filename passed is not recognized as a file or directory.")
+        exit()
 
+    print("Found files:")
+    pprint.pprint(files, indent=1)
+    make_graphs(files, True)
     plt.show()
\ No newline at end of file
diff --git a/tools/requirements.txt b/tools/requirements.txt
new file mode 100644
index 0000000..32691d7
--- /dev/null
+++ b/tools/requirements.txt
@@ -0,0 +1,2 @@
+pandas==1.5.2       # need >1.5 because of "step" in rolling() mean
+matplotlib==3.5.1
\ No newline at end of file
diff --git a/tools/usage.md b/tools/usage.md
new file mode 100644
index 0000000..d0dd358
--- /dev/null
+++ b/tools/usage.md
@@ -0,0 +1,12 @@
+To use install requirements  
+
+Works with python 3.10  
+    Should work with more recent  
+
+To set up local venv:  
+1. Create a local venv `python -m venv env`
+2. Active it (windows) `"./env/Scripts/activate.bat"`
+3. Install requirements `pip install -r requirements.txt`
+4. Run in script (need to active it or use current) `python graphing.py <dir/log filename>`
+  - Where dir is the folder for all the logs
+  - Where log filename is any specific log file set to use (will need all 5 outputs in the same directory)
\ No newline at end of file