exploration script

exploration.py

@@ -16,7 +16,7 @@ import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 import seaborn as sns
-
+#%matplotlib qt
 
 #%% set paths and constants and load data
 
@@ -24,10 +24,10 @@ import seaborn as sns
 path = os.path.join("W:","\ASG","WLR_Dataopslag","DairyCampus","3406_Nlas","uwb_processed")
 
 # settings
-settings = {'barn' : [60,61,62,70,71,72,73],
+settings = {'barn' : [71], # [60,61,62,70,71,72,73],
             'startdate' : date(2022,10,5),
-            'enddate' :  date(2022,12,30),
-            'cows' : [1790], # or specific cow number
+            'enddate' :  date(2022,10,30),
+            'cows' : [2433], # or specific cow number
             }
 
 # files that comply with settings
@@ -58,14 +58,23 @@ data = pd.DataFrame([])
 for f in fn:
     barn = f[19:21]
     sub = pd.read_csv(path + "/barn" + barn + "/" + f, 
-                      usecols = ["cowid","barn","date","t","xnew","ynew","area","zone"],
+                      usecols = ["cowid","barn","date","t","xnew","ynew","area","zone","X","y"],
                       dtype = {"cowid" : "int64","barn" : "int64","date" : "object",
                                "t" : "int64", "xnew":"float64","ynew":"float64",
-                               "area":"object","zone":"float64"})
+                               "area":"object","zone":"float64","X":"float64","y" : "float64"})
     sub["date"] = pd.to_datetime(sub["date"], format = "%Y-%m-%d") 
     data = pd.concat([data,sub])
 data = data.sort_values(by = ["cowid","date","t"])
 
+# summarize data per zone
+zones = data[["cowid","date","area","t"]].groupby(by = ["cowid","date","area"]).count().reset_index()
+zones = zones.sort_values(by = ["cowid","area"])
+
+# summarize variables
+data[["xnew","X","ynew","y"]].describe()
+test = data.loc[(data["ynew"] < -17) & (data["ynew"] > -19),:]
+sns.scatterplot(data=test, x = test.index.values, y = "ynew")
+sns.scatterplot(data=test, x = test.index.values, y = "y")