c='k',
marker='*')
ax.plot(X, spline_pred, 'r--', label="Spline")
ax.scatter(spline_max_DoYs_series,
spline_max_series,
s=100,
c='r',
marker='*')
################################################
#
# bare soil indices plots
#
an_EE_TS_BSI = rc.initial_clean(df=curr_field,
column_to_be_cleaned='BSI')
# an_EE_TS_NDWI = rc.initial_clean(df = curr_field, column_to_be_cleaned='NDWI')
an_EE_TS_PSRI = rc.initial_clean(df=curr_field,
column_to_be_cleaned='PSRI')
an_EE_TS_LSWI = rc.initial_clean(df=curr_field,
column_to_be_cleaned='LSWI')
ax.plot(an_EE_TS_BSI['doy'], an_EE_TS_BSI['BSI'], label="BSI")
# ax.plot(x_NDWI, y_NDWI, label="NWDI")
ax.plot(an_EE_TS_PSRI['doy'], an_EE_TS_PSRI['PSRI'], label="PSRI")
ax.plot(an_EE_TS_LSWI['doy'], an_EE_TS_LSWI['LSWI'], label="LSWI")
################################################
ax.legend(loc="best")
### process data
###
########################################################################################
f_name = "00_noOutlier_" + county + "_SF_" + str(
SF_year) + "_" + indeks + ".csv"
an_EE_TS = pd.read_csv(data_dir + f_name, low_memory=False)
########################################################################################
output_dir = data_base + "/01_jumps_removed/"
os.makedirs(output_dir, exist_ok=True)
########################################################################################
an_EE_TS = rc.initial_clean(df=an_EE_TS, column_to_be_cleaned=indeks)
an_EE_TS.head(2)
###
### List of unique polygons
###
polygon_list = an_EE_TS['ID'].unique()
print(len(polygon_list))
########################################################################################
###
### initialize output data.
###
output_df = pd.DataFrame(data=None,
index=np.arange(an_EE_TS.shape[0]),
print(an_EE_TS.county.unique())
an_EE_TS = an_EE_TS[an_EE_TS['county'] == "Grant"]
print(an_EE_TS.county.unique())
#
# The following columns do not exist in the old data
#
if not ('DataSrc' in a_df.columns):
print("Data source is being set to NA")
a_df['DataSrc'] = "NA"
if not ('CovrCrp' in a_df.columns):
print("Data source is being set to NA")
a_df['CovrCrp'] = "NA"
an_EE_TS_NDVI = rc.initial_clean(df=an_EE_TS, column_to_be_cleaned='NDVI')
an_EE_TS_EVI = rc.initial_clean(df=an_EE_TS, column_to_be_cleaned='EVI')
an_EE_TS_BSI = rc.initial_clean(df=an_EE_TS, column_to_be_cleaned='BSI')
an_EE_TS_NDWI = rc.initial_clean(df=an_EE_TS, column_to_be_cleaned='NDWI')
an_EE_TS_PSRI = rc.initial_clean(df=an_EE_TS, column_to_be_cleaned='PSRI')
an_EE_TS_LSWI = rc.initial_clean(df=an_EE_TS, column_to_be_cleaned='LSWI')
an_EE_TS_NDVI.head(2)
### List of unique polygons
polygon_list = an_EE_TS_NDVI['geo'].unique()
print(len(polygon_list))
counter = 0
for a_poly in polygon_list:
# if (filter_lastSurDate == True):
# a_df = rc.filter_out_NASS(dt_df_NASS = a_df)
# print ("After filtering out NASS, a_df is of dimension {fileShape}.".format(fileShape=a_df.shape))
######################
# a_df['year'] = SF_year
#
# The following columns do not exist in the old data
#
if not('DataSrc' in a_df.columns):
print ("_________________________________________________________")
print ("Data source is being set to NA")
a_df['DataSrc'] = "NA"
a_df = rc.initial_clean(df = a_df, column_to_be_cleaned = indeks)
a_df = a_df.copy()
### List of unique polygons
polygon_list = a_df['ID'].unique()
print ("_________________________________________________________")
print("polygon_list is of length {}.".format(len(polygon_list)))
#
# 25 columns
#
SEOS_output_columns = ['ID', 'Acres', 'county', 'CropGrp', 'CropTyp', 'DataSrc', 'ExctAcr',
'IntlSrD', 'Irrigtn', 'LstSrvD', 'Notes', 'RtCrpTy', 'Shap_Ar',
'Shp_Lng', 'TRS', 'image_year', 'SF_year', 'doy', 'EVI',
'human_system_start_time', 'Date',
os.makedirs(output_dir, exist_ok=True)
os.makedirs(plot_dir_base, exist_ok=True)
######################
# The following columns do not exist in the old data
#
if not ('CovrCrp' in a_df.columns):
print("Data source is being set to NA")
a_df['CovrCrp'] = "NA"
####################################################################################
an_EE_TS_NDVI = rc.initial_clean(df=a_df, column_to_be_cleaned='NDVI')
an_EE_TS_EVI = rc.initial_clean(df=a_df, column_to_be_cleaned='EVI')
an_EE_TS_BSI = rc.initial_clean(df=a_df, column_to_be_cleaned='BSI')
an_EE_TS_NDWI = rc.initial_clean(df=a_df, column_to_be_cleaned='NDWI')
an_EE_TS_PSRI = rc.initial_clean(df=a_df, column_to_be_cleaned='PSRI')
an_EE_TS_LSWI = rc.initial_clean(df=a_df, column_to_be_cleaned='LSWI')
an_EE_TS_NDVI = rc.add_human_start_time(an_EE_TS_NDVI)
an_EE_TS_EVI = rc.add_human_start_time(an_EE_TS_EVI)
an_EE_TS_BSI = rc.add_human_start_time(an_EE_TS_BSI)
an_EE_TS_NDWI = rc.add_human_start_time(an_EE_TS_NDWI)
an_EE_TS_PSRI = rc.add_human_start_time(an_EE_TS_PSRI)
an_EE_TS_LSWI = rc.add_human_start_time(an_EE_TS_LSWI)
####################################################################################