diff --git a/__pycache__/heatmap_visualisation.cpython-39.pyc b/__pycache__/heatmap_visualisation.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..8161ab61c997fbecdf290aa568589925a223abfd
Binary files /dev/null and b/__pycache__/heatmap_visualisation.cpython-39.pyc differ
diff --git a/exploration.py b/exploration.py
index 82d8c5b188525896a0f315070d4ad9bb41998b60..d7f5e529ecd64e327bbe4cd8ce235496d4cefb0b 100644
--- a/exploration.py
+++ b/exploration.py
@@ -11,11 +11,13 @@ os.chdir(r"C:\Users\adria036\OneDrive - Wageningen University & Research\iAdriae
#%% import modules
-from datetime import date, timedelta,datetime
+from datetime import date, datetime
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
+import matplotlib
import seaborn as sns
+from heatmap_visualisation import heatmap_barn
#%matplotlib qt
#%% set paths and constants and load data
@@ -165,12 +167,12 @@ for cow in cows:
plt.close()
-# summarize variables
-data[["xnew","X","ynew","y"]].describe()
-data[""]
-test = data.loc[(data["ynew"] < -17) & (data["ynew"] > -19) & (data["cowid"] = cow),:]
-sns.scatterplot(data=test, x = test.index.values, y = "ynew")
-sns.scatterplot(data=test, x = test.index.values, y = "y")
+# # summarize variables
+# data[["xnew","X","ynew","y"]].describe()
+# data[""]
+# test = data.loc[(data["ynew"] < -17) & (data["ynew"] > -19) & (data["cowid"] = cow),:]
+# sns.scatterplot(data=test, x = test.index.values, y = "ynew")
+# sns.scatterplot(data=test, x = test.index.values, y = "y")
@@ -183,13 +185,11 @@ sns.scatterplot(data=test, x = test.index.values, y = "y")
- explore gaps and gapsize
"""
-#gapsize
-
+#-------------------------------gapsize----------------------------------------
subset = data.loc[data["X"].isna(),["cowid","barn","date","t"]]
sumdata = subset.groupby(by = ["cowid","barn","date"]).count()
subset = data.loc[data["xnew"].isna(),["cowid","barn","date","t"]]
test = subset.groupby(by = ["cowid","barn","date"]).count()
-
sumdata["xnew"] = test["t"]
sumdata["gapperc"] = sumdata["t"]/864
@@ -209,10 +209,173 @@ ax = sns.scatterplot(data=sumdata,x = "xlabel", y = "gap180s",
palette = "tab10", hue = "cowid",
style = "date", legend = False)
plt.savefig(svpath + "\\gap_imputed.png")
-# average gap
+
+
+#------------------------------behaviour over 24h------------------------------
+#sns.set_style("darkgrid") # whitegrid, dark, white, ticks
+
+cows = data["cowid"].drop_duplicates().reset_index(drop=1)
+for cow in cows:
+ print(cow)
+ days = data.loc[(data["cowid"]==cow),["date"]].drop_duplicates()
+ days = days.sort_values(by = ["date"]).reset_index(drop=1)
+
+ for dd in days["date"]:
+ print(dd)
+ subset = data.loc[(data["cowid"]==cow) & \
+ (data["date"]==dd),:].copy()
+ palette = {"walking" : "darkorange",
+ "concentrate " : "tan",
+ "cubicle_A" : "darkorchid",
+ "cubicle_B" : "violet",
+ "cubicle_C" : "palevioletred",
+ "feed_rack" : "crimson",
+ "drink_trough" : "gold",
+ "slatted" : "limegreen",
+ "resting" : "darkorchid",
+ "waiting_area" : "mediumseagreen",
+ "unknown" : "royalblue"}
+ fig,ax = plt.subplots(1,1,figsize = (18,7))
+ sns.scatterplot(data=subset,x="t",y="zone",
+ hue="area",
+ marker = "s", linewidth = 0,
+ palette = palette,
+ legend = False)
+ sns.lineplot(data=subset, x='t',y = 'zone',
+ linewidth = 0.2, color = 'k')
+ ax.set_yticks(range(9))
+ ax.set_yticklabels(["walking","cubicles","feed rack","drink trough",
+ "concentrate feeder","slatted (b62)","resting (b62)",
+ "waiting area","unknown"])
+ sns.set_style("ticks")
+ ax.set_xticks([0,14400,28800,43200,57600,72000,86400])
+ ax.set_xticklabels(['00:00','04:00','08:00','12:00','16:00','20:00','24:00'])
+ ax.set_xlabel("time [h]")
+ ax.set_title("cow = " + str(cow) + ', date = ' + str(dd))
+ ax.set_xlim([-1000,87400])
+ plt.savefig(svpath+"\\timebudget_cow_" + str(cow) + "_" + str(dd).replace("-","") + ".png")
+ plt.close()
+
+
+# ------------------------- individual cow heatmaps ---------------------------
+cows = data["cowid"].drop_duplicates().reset_index(drop=1)
+#barn limits
+barn = {"60":[64.8,75.6],
+ "61":[54,64.8],
+ "62":[32.4,54],
+ "70":[21.6,32.4],
+ "71":[10.8,21.6],
+ "72":[0,10.8],
+ "73":[-10.8,0],
+ }
+# plots per cow-day
+for cow in cows["cowid"]:
+ # unique days
+ days = data.loc[(data["cowid"]==cow),["date"]].drop_duplicates()
+ days = days.sort_values(by = ["date"]).reset_index(drop=1)
+
+ # select data and create heatmaps
+ for dd in days["date"]:
+ print(cow, dd)
+ # select data
+ data_x = data.loc[(data["cowid"] == cow) &
+ (data["date"] == dd),"X"]
+ data_y = data.loc[(data["cowid"] == cow) &
+ (data["date"] == dd),"y"]
+
+ # set limits (based on information barn)
+ barnnr = int(data.loc[(data["cowid"] == cow) &
+ (data["date"] == dd),"barn"].mean())
+ x_lim = barn[str(barnnr)]
+ y_lim = [-18,0]
+
+ # plot heatmap
+ # matplotlib.rcdefaults()
+ fig, ax = plt.subplots()
+ ax = heatmap_barn(data_x, data_y, 0.1, 0.1, x_lim, y_lim)
+ ax.set_xlabel('y coordinate')
+ ax.set_ylabel('x coordinate')
+ ax.set_title("barn = " +str(barnnr) + ', cow = ' + str(cow) + \
+ ", date = " + datetime.strftime(dd,"%Y-%m-%d").replace("-",""))
+ ax.xaxis.tick_top()
+ plt.savefig(svpath + "//heatmap_" + str(cow) + "_" + str(dd).replace("-",""))
+ plt.close()
+
+
+#------------------combine heatmap with budget-area over time------------------
+#barn limits
+barn = {"60":[64.8,75.6],
+ "61":[54,64.8],
+ "62":[32.4,54],
+ "70":[21.6,32.4],
+ "71":[10.8,21.6],
+ "72":[0,10.8],
+ "73":[-10.8,0],
+ }
+palette = {"walking" : "darkorange",
+ "concentrate " : "tan",
+ "cubicle_A" : "darkorchid",
+ "cubicle_B" : "violet",
+ "cubicle_C" : "palevioletred",
+ "feed_rack" : "crimson",
+ "drink_trough" : "gold",
+ "slatted" : "limegreen",
+ "resting" : "darkorchid",
+ "waiting_area" : "mediumseagreen",
+ "unknown" : "royalblue"}
+cows = data["cowid"].drop_duplicates().reset_index(drop=1)
+for cow in cows:
+ print(cow)
+ days = data.loc[(data["cowid"]==cow),["date"]].drop_duplicates()
+ days = days.sort_values(by = ["date"]).reset_index(drop=1)
+
+ for dd in days["date"]:
+ print(dd)
+ subset = data.loc[(data["cowid"]==cow) & \
+ (data["date"]==dd),:].copy()
+
+ fig, ax = plt.subplots(1, 2, gridspec_kw={'width_ratios': [3, 1.5]}, figsize = (22,7))
+ # plot scatter + line
+ sns.scatterplot(data=subset,x="t",y="zone",
+ hue="area",
+ marker = "s", linewidth = 0,
+ palette = palette,
+ legend = False,
+ ax = ax[0])
+ sns.lineplot(data=subset, x='t',y = 'zone',
+ linewidth = 0.2, color = 'k', ax = ax[0])
+ ax[0].set_yticks(range(9))
+ ax[0].set_yticklabels(["walking","cubicles","feed rack","drink trough",
+ "concentrate feeder","slatted (b62)","resting (b62)",
+ "waiting area","unknown"])
+ sns.set_style("ticks")
+ ax[0].set_xticks([0,14400,28800,43200,57600,72000,86400])
+ ax[0].set_xticklabels(['00:00','04:00','08:00','12:00','16:00','20:00','24:00'])
+ ax[0].set_xlabel("time [h]")
+ ax[0].set_title("cow = " + str(cow) + ', date = ' + str(dd))
+ ax[0].set_xlim([-1000,87400])
+
+ # set limits (based on information barn)
+ barnnr = int(data.loc[(data["cowid"] == cow) &
+ (data["date"] == dd),"barn"].mean())
+ x_lim = barn[str(barnnr)]
+ y_lim = [-18,0]
+
+ # plot heatmap
+ ax[1] = heatmap_barn(subset["xnew"], subset["ynew"], 0.1, 0.1, x_lim, y_lim)
+ ax[1].set_xlabel('y coordinate')
+ ax[1].set_ylabel('x coordinate')
+ ax[1].set_title("barn = " +str(barnnr) + ', cow = ' + str(cow) + \
+ ", date = " + str(dd))
+ ax[1].xaxis.tick_top()
+ ax[1].yaxis.tick_right()
+ ax[1].yaxis.set_label_position("right")
+
+ plt.savefig(svpath+"\\spatial_cow_" + str(cow) + "_" + str(dd).replace("-","") + ".png")
+ plt.close()
\ No newline at end of file
diff --git a/heatmap_visualisation.py b/heatmap_visualisation.py
index 0cf37a0bdcf91e08d133354f0d7778521463a1d6..d49d6d232408acbd8f814523b027bcaef25b0292 100644
--- a/heatmap_visualisation.py
+++ b/heatmap_visualisation.py
@@ -12,7 +12,8 @@ import numpy as np
# from read_data_sewio import start_end_dates, read_all_data, read_ids, combine_data_id
import os
import seaborn as sns
-import matplotlib as plt
+import matplotlib
+import matplotlib.pyplot as plt
# path_out
@@ -113,11 +114,15 @@ def heatmap_barn(data_x,data_y,xstep,ystep,x_lim,y_lim):
ax = sns.heatmap(df,
yticklabels = round(1/xstep),
xticklabels = round(1/ystep*2),
- robust = True
+ robust = True,
+ cbar = False
)
return ax
+
+
+"""
#%% usage
# ------------------------- individual cow heatmaps ---------------------------
# unique cows
@@ -163,14 +168,14 @@ for cow in cows["cowid"]:
y_lim = [-18,0] #[data_y.min(),data_y.max()]
# plot heatmap
- plt.rcdefaults()
- fig, ax = plt.pyplot.subplots()
+ matplotlib.rcdefaults()
+ fig, ax = plt.subplots()
ax = heatmap_barn(data_x, data_y, xstep, ystep, x_lim, y_lim)
ax.set_xlabel('y coordinate')
ax.set_ylabel('x coordinate')
ax.set_title("barn = " +str(barnnr) + ', cow = ' + str(cow) + ", date = " + datetime.strftime(dd,"%Y-%m-%d").replace("-",""))
ax.xaxis.tick_top()
- plt.pyplot.savefig(path_out + "//heatmap_" + str(cow) + "_" + datetime.strftime(dd,"%Y-%m-%d").replace("-",""))
- plt.pyplot.close()
-
+ plt.savefig(path_out + "//heatmap_" + str(cow) + "_" + datetime.strftime(dd,"%Y-%m-%d").replace("-",""))
+ plt.close()
+"""