def main_data(start, end, **kwargs):
span = kwargs["span"]
region = kwargs["region"]
get_columns = kwargs["get_columns"]
accumulate = kwargs["accumulate"]
date_ax, date_ax_str = get_date_ax(start, end)
N = len(date_ax_str)
skipping_date_str = []
accumulate_data = []
data = []
for i, day in enumerate(date_ax_str):
print("{}/{}: {}".format(i + 1, N, day))
print("start: {}, end: {}".format(start, end))
year = day[2:4]
month = day[4:6]
#ファイル名の生成
wind_file_name = "../data/csv_w/ecm" + day[2:] + ".csv"
ice_file_name = "../data/csv_iw/" + day[2:] + ".csv"
ic0_145_file_name = "../data/csv_ic0/IC0_" + day + ".csv"
sit_145_file_name = "../data/csv_sit/SIT_" + day + ".csv"
coeff_file_name = "../data/csv_A_30/ssc_amsr_ads" + str(year) + str(
month) + "_" + str(span) + "_fin.csv"
hermert_file_name = "../data/csv_Helmert_30/Helmert_30_" + str(
day)[:6] + ".csv"
# wind10m_file_name = "../data/netcdf4/" + day[2:] + ".csv"
# t2m_file_name = "../data/netcdf4/" + day[2:] + ".csv"
skipping_boolean = ("coeff" not in get_columns) and (not all([
os.path.isfile(wind_file_name),
os.path.isfile(ice_file_name),
os.path.isfile(coeff_file_name)
]))
if ("ic0_145" in get_columns):
skipping_boolean = ("coeff" not in get_columns) and (not all([
os.path.isfile(wind_file_name),
os.path.isfile(ice_file_name),
os.path.isfile(coeff_file_name),
os.path.isfile(ic0_145_file_name)
]))
if ("sit_145" in get_columns):
skipping_boolean = ("coeff" not in get_columns) and (not all([
os.path.isfile(wind_file_name),
os.path.isfile(ice_file_name),
os.path.isfile(coeff_file_name),
os.path.isfile(sit_145_file_name)
]))
if skipping_boolean == True:
print("\tSkipping " + day + " file...")
date_ax_str.remove(day)
bb = date(int(day[:4]), int(day[4:6]), int(day[6:]))
date_ax.remove(bb)
skipping_date_str.append(day)
continue
data = pd.DataFrame({"data_idx": np.array(ocean_grid_145).ravel()})
if "ex_1" in get_columns:
print("\t{}\n\t{}\n\t{}\n\t{}".format(wind_file_name,
ice_file_name,
coeff_file_name))
tmp = calc_data.get_w_regression_data(wind_file_name,
ice_file_name,
coeff_file_name)
data = pd.concat([data, tmp], axis=1)
if "ex_2" in get_columns:
print("\t{}\n\t{}\n\t{}\n\t{}".format(wind_file_name,
ice_file_name,
hermert_file_name))
tmp = calc_data.get_w_hermert_data(wind_file_name, ice_file_name,
hermert_file_name)
data = pd.concat([data, tmp], axis=1)
if "w" in get_columns:
print("\t{}".format(wind_file_name))
tmp = calc_data.get_1day_w_data(wind_file_name)
data = pd.concat([data, tmp], axis=1)
if "iw" in get_columns:
print("\t{}".format(ice_file_name))
tmp = calc_data.get_1day_iw_data(ice_file_name)
data = pd.concat([data, tmp], axis=1)
if "ic0_145" in get_columns:
print("\t{}".format(ic0_145_file_name))
tmp = calc_data.get_1day_ic0_data(ic0_145_file_name)
data = pd.concat([data, tmp], axis=1)
if "sit_145" in get_columns:
print("\t{}".format(sit_145_file_name))
tmp = calc_data.get_1day_sit_data(sit_145_file_name)
data = pd.concat([data, tmp], axis=1)
if "coeff" in get_columns:
print("\t{}".format(coeff_file_name))
tmp = calc_data.get_1month_coeff_data(coeff_file_name)
data = pd.concat([data, tmp], axis=1)
if "hermert" in get_columns:
print("\t{}".format(hermert_file_name))
tmp = calc_data.get_1month_hermert_data(hermert_file_name)
data = pd.concat([data, tmp], axis=1)
"""
if "w10m" in get_columns:
tmp = calc_data.get_1day_w10m_data(wind10m_file_name)
data = pd.concat([data, tmp], axis=1)
if "t2m" in get_columns:
tmp = calc_data.get_1day_t2m_data(t2m_file_name)
data = pd.concat([data, tmp], axis=1)
"""
data = calc_data.get_masked_region_data(data, region)
if ("coeff" in get_columns):
print("\tSelected only coeff data. Getting out of the loop...")
continue
if accumulate == True:
data_1 = data.drop("data_idx", axis=1)
print("\t{}".format(data_1.columns))
accumulate_data.append(np.array(data_1))
if accumulate == True:
print("accumulate: True\tdata type: array")
return date_ax, date_ax_str, skipping_date_str, accumulate_data
else:
print("accumulate: False\tdata type: DataFrame")
return date_ax, date_ax_str, skipping_date_str, data
def H_ts_A_month():
def plot_param_1g(save_name):
plot_param_list = ["A", "theta", "epsilon2"]
for i, item in enumerate(plot_param_list):
plot_data_1g = data_m_1g[item].loc[:, ["mean", "std", "50%"]]
plot_data_1g["2sigma_pos"] = plot_data_1g['mean']+2*np.sqrt(plot_data_1g['std'])
plot_data_1g["2sigma_neg"] = plot_data_1g['mean']-2*np.sqrt(plot_data_1g['std'])
dates = pd.date_range("2013", periods=12, freq='MS')
plot_data_1g["Month"] = dates
fig, ax = plt.subplots()
plt.subplot(311+i)
ax.plot(dates, plot_data_1g['mean'], '-')
ax.plot(dates, plot_data_1g["2sigma_pos"], '-')
ax.plot(dates, plot_data_1g["2sigma_neg"], '-')
ax.xaxis.set_major_formatter(mdates.DateFormatter('%m'))
d = plot_data_1g['Month'].values
plt.fill_between(d, plot_data_1g['2sigma_pos'], plot_data_1g['2sigma_neg'],
facecolor='green', alpha=0.2, interpolate=True)
plt.savefig(save_name)
plt.close()
def plot_param_2g(save_name):
plot_param_list = ["A", "theta", "epsilon2"]
for i, item in enumerate(plot_param_list):
for j, is_np in enumerate([1,0]):
plot_data_2g_np_pos = data_m_2g.loc[(is_np), (item, ["mean", "std", "50%"])]
plot_data_2g_np_pos["2sigma_pos"] = plot_data_2g_np_pos['mean']+2*np.sqrt(plot_data_2g_np_pos['std'])
plot_data_2g_np_pos["2sigma_neg"] = plot_data_2g_np_pos['mean']-2*np.sqrt(plot_data_2g_np_pos['std'])
plot_data_2g_np_pos["Month"] = np.arange(1, 13, 1)
plt.subplot(321+j+i*2)
plt.plot_date(plot_data_2g_np_pos['Month'], plot_data_2g_np_pos['mean'], '-')
plt.plot_date(plot_data_2g_np_pos['Month'], plot_data_2g_np_pos["2sigma_pos"], '-')
plt.plot_date(plot_data_2g_np_pos['Month'], plot_data_2g_np_pos["2sigma_neg"], '-')
d = plot_data_2g_np_pos['Month'].values
plt.fill_between(d, plot_data_2g_np_pos['2sigma_pos'], plot_data_2g_np_pos['2sigma_neg'],
facecolor='green', alpha=0.2, interpolate=True)
plt.savefig(save_name)
plt.close()
def plot_param_3g(plot_param_item, save_name):
for i, is_np in enumerate([1, 0]):
plot_data_3g_np_pos = data_m_2g.loc[(is_np), (plot_param_item, ["mean", "std", "50%"])]
plot_data_3g_np_pos["2sigma_pos"] = plot_data_3g_np_pos[(plot_param_item, "mean")] + 2*np.sqrt(plot_data_3g_np_pos[(plot_param_item, "std")])
plot_data_3g_np_neg["2sigma_neg"] = plot_data_3g_np_neg[(plot_param_item, "mean")] - 2*np.sqrt(plot_data_3g_np_neg[(plot_param_item, "std")])
#plot_data_3g_np_neg["Month"] = np.arange(1, 13, 1)
for j, subplot_idx in enumerate([0,1,2]):
plt.subplot(321+i+subplot_idx*2)
plt.plot_date(np.arange(1, 13, 1), plot_data_3g_np_pos.loc[(j), (plot_param_item, "mean")], '-')
plt.plot_date(np.arange(1, 13, 1), plot_data_3g_np_pos.loc[(j), ("2sigma_pos")], '-')
plt.plot_date(np.arange(1, 13, 1), plot_data_3g_np_pos.loc[(j), ("2sigma_neg")], '-')
plt.fill_between(np.arange(1, 13, 1), plot_data_3g_np_pos.loc[(j), ("2sigma_pos")], plot_data_3g_np_pos.loc[(j), ("2sigma_neg")],
facecolor='green', alpha=0.2, interpolate=True)
plt.savefig(save_name)
plt.close()
y_list = ["03", "04", "05", "06", "07", "08", "09", "10", "13", "14", "15", "16"]
month_list = ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"]
for y in y_list:
data_m = pd.DataFrame([])
for m in month_list:
yymm = "20" + y + m
hermert_file_name = "../data/csv_Helmert_30/Helmert_30_" + yymm + ".csv"
data = calc_data.get_1month_hermert_data(hermert_file_name)
data = pd.concat([latlon_ex["Name"], data], axis=1)
#data = data.drop(["Lat", "Lon", "Label", "idx1", "idx2"], axis=1)
rank_np = np.zeros(145**2)
rank_np[data[data.Name=="north_polar"].index] = 1
data["rank_np"] = rank_np
rank_R2 = np.ones(145**2)
rank_R2[data[data.R2<=(1/3)**2].index] = 0
rank_R2[data[data.R2>(2/3)**2].index] = 2
data["rank_R2"] = rank_R2
data = data.dropna()
#https://code.i-harness.com/ja/q/1c29878
print(data.isnull().sum().sum())
data["yymm"] = [pd.to_datetime(yymm, format="%Y%m")] * len(data)
data_m = pd.concat([data_m, data])
"""
describe_data = data.groupby("rank_np")[["A", "theta", "epsilon2"]].describe()
describe_data = data.groupby("rank_np").agg({
'A': [np.nanmean, np.nanstd, np.nanmedian],
'theta': [np.nanmean, np.nanstd, np.nanmedian],
'epsilon2': [np.nanmean, np.nanstd, np.nanmedian]
})
pd.concat([data_all, data.loc[:, ["A", "theta", "epsilon2"]]])
data_m.append(np.array(data.loc[:, ["A", "theta", "epsilon2"]]))
"""
#data_m = np.array(data_m)
#月ごとに全てのエリアの平均などを取得
data_m_1g = data_m.groupby("yymm")[["A", "theta", "epsilon2"]].describe().sort_index(level='yymm')
#月ごとにrank_npで分類したものを取得
data_m_2g = data_m.groupby(["rank_np", "yymm"])[["A", "theta", "epsilon2"]].describe().sort_index(level='yymm')
#月ごとにrank_npとrank_R2で分類したものを取得
data_m_3g = data_m.groupby(["rank_np", "rank_R2", "yymm"])[["A", "theta", "epsilon2"]].describe().sort_index(level='yymm')
#1gのプロット
plot_param_1g(save_name)
#2gのプロット
plot_param_2g(save_name)
#3gのプロット
plot_param_list = ["A", "theta", "epsilon2"]
for item in plot_param_list:
plot_param_3g(item, save_name)
"""
#data_m_A = data_m[:,:,0].T
#A_ave = np.nanmean(data_m_A, axis=0)
#A_std = np.nanstd(data_m_A, axis=0)
#https://stackoverflow.com/questions/29329725/pandas-and-matplotlib-fill-between-vs-datetime64
yydd_str = "20" + y
tmp = pd.to_datetime(["20" + y + m for m in month_list])
dates = pd.date_range(yydd_str, periods=12, freq='M')
#dates = pd.to_datetime(["20" + y + m for m in month_list], format="%Y%m")
data = pd.DataFrame({"A_ave": A_ave, "A_std": A_std, "Date": dates})
data["A_2sigma_pos"] = data['A_ave']+2*data['A_std']
data["A_2sigma_neg"] = data['A_ave']-2*data['A_std']
plt.figure()
plt.plot_date(data['Date'], data['A_ave'], '-')
plt.plot_date(data['Date'], data["A_2sigma_pos"], '-')
plt.plot_date(data['Date'], data["A_2sigma_neg"], '-')
d = data['Date'].values
plt.fill_between(d, data['A_2sigma_pos'], data['A_2sigma_neg'],
facecolor='green', alpha=0.2, interpolate=True)
plt.xticks(rotation=25)
"""
#http://pandas.pydata.org/pandas-docs/version/0.15.0/visualization.html
"""
plt.plot(price.index, price, 'k')
plt.plot(ma.index, ma, 'b')
plt.fill_between(mstd.index, ma-2*mstd, ma+2*mstd, color='b', alpha=0.2)
"""
"""
def H_ts_A_year():
def y_plot_param_1g(save_name):
plot_param_list = ["A", "theta", "epsilon2"]
for i, item in enumerate(plot_param_list):
plot_data_1g = data_m_1g[item].loc[:, ["mean", "std", "50%"]]
plot_data_1g["2sigma_pos"] = plot_data_1g['mean']+2*np.sqrt(plot_data_1g['std'])
plot_data_1g["2sigma_neg"] = plot_data_1g['mean']-2*np.sqrt(plot_data_1g['std'])
plot_data_1g["Year"] = np.array([2003,2004,2005,2006,2007,2008,2009,2010,2013,2014,2015,2016])
plt.subplot(311+i)
plt.plot_date(plot_data_1g['Year'], plot_data_1g['mean'], '-')
plt.plot_date(plot_data_1g['Year'], plot_data_1g["2sigma_pos"], '-')
plt.plot_date(plot_data_1g['Year'], plot_data_1g["2sigma_neg"], '-')
d = plot_data_1g['Year'].values
plt.fill_between(d, plot_data_1g['2sigma_pos'], plot_data_1g['2sigma_neg'],
facecolor='green', alpha=0.2, interpolate=True)
plt.savefig(save_name)
plt.close()
def y_plot_param_2g(save_name):
plot_param_list = ["A", "theta", "epsilon2"]
for i, item in enumerate(plot_param_list):
for j, is_np in enumerate([1,0]):
plot_data_2g_np_pos = data_m_2g.loc[(is_np), (item, ["mean", "std", "50%"])]
plot_data_2g_np_pos["2sigma_pos"] = plot_data_2g_np_pos['mean']+2*np.sqrt(plot_data_2g_np_pos['std'])
plot_data_2g_np_pos["2sigma_neg"] = plot_data_2g_np_pos['mean']-2*np.sqrt(plot_data_2g_np_pos['std'])
plot_data_2g_np_pos["Year"] = np.array([2003,2004,2005,2006,2007,2008,2009,2010,2013,2014,2015,2016])
plt.subplot(321+j+i*2)
plt.plot_date(plot_data_2g_np_pos['Year'], plot_data_2g_np_pos['mean'], '-')
plt.plot_date(plot_data_2g_np_pos['Year'], plot_data_2g_np_pos["2sigma_pos"], '-')
plt.plot_date(plot_data_2g_np_pos['Year'], plot_data_2g_np_pos["2sigma_neg"], '-')
d = plot_data_2g_np_pos['Year'].values
plt.fill_between(d, plot_data_2g_np_pos['2sigma_pos'], plot_data_2g_np_pos['2sigma_neg'],
facecolor='green', alpha=0.2, interpolate=True)
plt.savefig(save_name)
plt.close()
def y_plot_param_3g(plot_param_item, save_name):
for i, is_np in enumerate([1, 0]):
plot_data_3g_np_pos = data_m_2g.loc[(is_np), (plot_param_item, ["mean", "std", "50%"])]
plot_data_3g_np_pos["2sigma_pos"] = plot_data_3g_np_pos[(plot_param_item, "mean")] + 2*np.sqrt(plot_data_3g_np_pos[(plot_param_item, "std")])
plot_data_3g_np_neg["2sigma_neg"] = plot_data_3g_np_neg[(plot_param_item, "mean")] - 2*np.sqrt(plot_data_3g_np_neg[(plot_param_item, "std")])
#plot_data_3g_np_neg["Month"] = np.arange(1, 13, 1)
year_array = np.array([2003,2004,2005,2006,2007,2008,2009,2010,2013,2014,2015,2016])
for j, subplot_idx in enumerate([0,1,2]):
plt.subplot(321+i+subplot_idx*2)
plt.plot_date(year_array, plot_data_3g_np_pos.loc[(j), (plot_param_item, "mean")], '-')
plt.plot_date(year_array, plot_data_3g_np_pos.loc[(j), ("2sigma_pos")], '-')
plt.plot_date(year_array, plot_data_3g_np_pos.loc[(j), ("2sigma_neg")], '-')
plt.fill_between(year_array, plot_data_3g_np_pos.loc[(j), ("2sigma_pos")], plot_data_3g_np_pos.loc[(j), ("2sigma_neg")],
facecolor='green', alpha=0.2, interpolate=True)
plt.savefig(save_name)
plt.close()
y_list = ["03", "04", "05", "06", "07", "08", "09", "10", "13", "14", "15", "16"]
month_list = ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"]
for m in month_list:
data_m = pd.DataFrame([])
for y in y_list:
yymm = "20" + y + m
hermert_file_name = "../data/csv_Helmert_30/Helmert_30_" + yymm + ".csv"
data = calc_data.get_1month_hermert_data(hermert_file_name)
data = pd.concat([latlon_ex["Name"], data], axis=1)
#data = data.drop(["Lat", "Lon", "Label", "idx1", "idx2"], axis=1)
rank_np = np.zeros(145**2)
rank_np[data[data.Name=="north_polar"].index] = 1
data["rank_np"] = rank_np
rank_R2 = np.ones(145**2)
rank_R2[data[data.R2<=(1/3)**2].index] = 0
rank_R2[data[data.R2>(2/3)**2].index] = 2
data["rank_R2"] = rank_R2
data = data.dropna()
#https://code.i-harness.com/ja/q/1c29878
print(data.isnull().sum().sum())
data["Year"] = [int("20"+y)] * len(data)
data_m = pd.concat([data_m, data])
#年ごとに全てのエリアの平均などを取得
data_m_1g = data_m.groupby("Year")[["A", "theta", "epsilon2"]].describe().sort_index(level='Year')
#年ごとにrank_npで分類したものを取得
data_m_2g = data_m.groupby(["rank_np", "Year"])[["A", "theta", "epsilon2"]].describe().sort_index(level='Year')
#年ごとにrank_npとrank_R2で分類したものを取得
data_m_3g = data_m.groupby(["rank_np", "rank_R2", "Year"])[["A", "theta", "epsilon2"]].describe().sort_index(level='Year')
#1gのプロット
y_plot_param_1g(save_name)
#2gのプロット
y_plot_param_2g(save_name)
#3gのプロット
plot_param_list = ["A", "theta", "epsilon2"]
for item in plot_param_list:
y_plot_param_3g(item, save_name)
def H_ts_A_month(m_plot=True, y_plot=True):
dirs_1g = "../result_h/H_ts_month_1g/"
mkdir(dirs_1g)
dirs_2g = "../result_h/H_ts_month_2g/"
mkdir(dirs_2g)
dirs_3g = "../result_h/H_ts_month_3g/"
mkdir(dirs_3g)
dirs_year = "../result_h/H_ts_year/"
mkdir(dirs_year)
def plot_param_1g(data_m_1g, save_name):
fig, axes = plt.subplots(3, 1)
dates = pd.date_range("2001", periods=12, freq='MS')
plot_data_1g = data_m_1g["A"].loc[:, ["mean", "std", "50%"]]
plot_data_1g["2sigma_pos"] = plot_data_1g['mean'] + 1 * np.sqrt(
plot_data_1g['std'])
plot_data_1g["2sigma_neg"] = plot_data_1g['mean'] - 1 * np.sqrt(
plot_data_1g['std'])
#plot_data_1g["Month"] = dates
axes[0].plot(dates, plot_data_1g['mean'], '-', color="k")
#d = plot_data_1g['Month'].values
axes[0].fill_between(dates,
plot_data_1g['2sigma_pos'],
plot_data_1g['2sigma_neg'],
facecolor='green',
alpha=0.3,
interpolate=True)
#axes[0].set_ylim([0, 0.025])
axes[0].set_ylabel('A')
#axes[0].set_title('A, ' + str_year)
axes[0].xaxis.set_major_formatter(mdates.DateFormatter('%m'))
plot_data_1g_theta = data_m_1g["theta"].loc[:, ["mean", "std", "50%"]]
plot_data_1g_theta["2sigma_pos"] = plot_data_1g_theta[
'mean'] + 2 * np.sqrt(plot_data_1g_theta['std'])
plot_data_1g_theta["2sigma_neg"] = plot_data_1g_theta[
'mean'] - 2 * np.sqrt(plot_data_1g_theta['std'])
axes[1].plot(dates, plot_data_1g_theta['mean'], '-', color="k")
axes[1].fill_between(dates,
plot_data_1g_theta['2sigma_pos'],
plot_data_1g_theta['2sigma_neg'],
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
#axes[1].set_ylim([-180, 180])
axes[1].set_ylim([-60, 60])
#axes[1].set_yticks([-180, -120, -60, 0, 60, 120, 180])
axes[1].set_ylabel('theta')
#axes[1].set_title('theta, ' + str_year)
axes[1].xaxis.set_major_formatter(mdates.DateFormatter('%m'))
plot_data_1g_e2 = data_m_1g["epsilon2"].loc[:, ["mean", "std", "50%"]]
plot_data_1g_e2["2sigma_pos"] = plot_data_1g_e2['mean'] + 2 * np.sqrt(
plot_data_1g_e2['std'])
plot_data_1g_e2["2sigma_neg"] = plot_data_1g_e2['mean'] - 2 * np.sqrt(
plot_data_1g_e2['std'])
axes[2].plot(dates, plot_data_1g_e2['mean'], '-', color="k")
axes[2].fill_between(dates,
plot_data_1g_e2['2sigma_pos'],
plot_data_1g_e2['2sigma_neg'],
facecolor='silver',
alpha=0.3,
interpolate=True)
#axes[2].set_ylim([-180, 180])
#axes[2].set_yticks([-180, -120, -60, 0, 60, 120, 180])
axes[2].set_ylabel('e2')
#axes[2].set_title('e2, ' + str_year)
axes[2].xaxis.set_major_formatter(mdates.DateFormatter('%m'))
#plt.setp(axes[0].get_xticklabels(), visible=False)
#plt.setp(axes[1].get_xticklabels(), visible=False)
plt.tight_layout()
plt.savefig(save_name, dpi=900)
plt.close()
def plot_param_2g(data_m_2g, save_name):
plot_param_list = ["A", "theta", "epsilon2"]
fig, axes = plt.subplots(3, 2)
dates = pd.date_range("2001", periods=12, freq='MS')
axes[0, 0].set_title("Polar Region")
axes[0, 1].set_title("Coastal Region")
for i, item in enumerate(plot_param_list):
for j, is_np in enumerate([1, 0]):
plot_data_2g_np_pos = data_m_2g.loc[(is_np),
(item,
["mean", "std", "50%"])]
plot_data_2g_np_pos["2sigma_pos"] = plot_data_2g_np_pos[
(item,
'mean')] + 2 * np.sqrt(plot_data_2g_np_pos[(item, 'std')])
plot_data_2g_np_pos["2sigma_neg"] = plot_data_2g_np_pos[
(item,
'mean')] - 2 * np.sqrt(plot_data_2g_np_pos[(item, 'std')])
#plot_data_2g_np_pos["Month"] = np.arange(1, 13, 1)
ax = axes[i, j]
#plt.subplot(321+j+i*2)
ax.plot_date(dates,
plot_data_2g_np_pos[(item, 'mean')],
'-',
color="k")
#d = plot_data_2g_np_pos['Month'].values
ax.fill_between(dates,
plot_data_2g_np_pos['2sigma_pos'],
plot_data_2g_np_pos['2sigma_neg'],
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
if i == 0:
ax.set_ylim([0, 0.025])
#ax.set_yticks([0, 0.025])
elif i == 1:
ax.set_ylim([-180, 180])
ax.set_yticks([-180, -120, -60, 0, 60, 120, 180])
elif i == 2:
ax.set_ylim([0, 1.5])
#ax.set_yticks([0, 0.025])
ax.xaxis.set_major_formatter(mdates.DateFormatter('%m'))
axes[0, 0].set_ylabel('A')
axes[1, 0].set_ylabel('theta')
axes[2, 0].set_ylabel('e2')
axes[2, 0].set_xlabel("Month")
axes[2, 1].set_xlabel("Month")
"""
plt.setp(axes[0, 0].get_xticklabels(), visible=False)
plt.setp(axes[1, 0].get_xticklabels(), visible=False)
plt.setp(axes[0, 1].get_xticklabels(), visible=False)
plt.setp(axes[1, 1].get_xticklabels(), visible=False)
plt.setp(axes[0, 1].get_yticklabels(), visible=False)
plt.setp(axes[1, 1].get_yticklabels(), visible=False)
plt.setp(axes[2, 1].get_yticklabels(), visible=False)
"""
plt.tight_layout()
plt.savefig(save_name, dpi=900)
plt.close()
def plot_param_3g(data_m_3g, plot_param_item, save_name):
fig, axes = plt.subplots(3, 2)
dates = pd.date_range("2001", periods=12, freq='MS')
axes[0, 0].set_title("Polar Region")
axes[0, 1].set_title("Coastal Region")
for i, is_np in enumerate([1, 0]):
plot_data_3g_np_pos = data_m_3g.loc[(is_np),
(plot_param_item,
["mean", "std", "50%"])]
plot_data_3g_np_pos["2sigma_pos"] = plot_data_3g_np_pos[
(plot_param_item, "mean")] + 2 * np.sqrt(plot_data_3g_np_pos[
(plot_param_item, "std")])
plot_data_3g_np_pos["2sigma_neg"] = plot_data_3g_np_pos[
(plot_param_item, "mean")] - 2 * np.sqrt(plot_data_3g_np_pos[
(plot_param_item, "std")])
for j, subplot_idx in enumerate([2, 1, 0]):
ax = axes[j, i]
ax.plot(dates,
plot_data_3g_np_pos.loc[(subplot_idx),
(plot_param_item, "mean")],
'-',
color="k")
ax.fill_between(dates,
plot_data_3g_np_pos.loc[(subplot_idx),
("2sigma_pos")],
plot_data_3g_np_pos.loc[(subplot_idx),
("2sigma_neg")],
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
if plot_param_item == "A":
for ax in axes:
ax.set_ylim([0, 0.025])
elif plot_param_item == "theta":
for ax in axes:
ax.set_ylim([-180, 180])
ax.set_yticks([-180, -120, -60, 0, 60, 120, 180])
elif plot_param_item == "e2":
for ax in axes:
ax.set_ylim([0, 1.5])
axes[0, 0].set_ylabel('R2 High')
axes[1, 0].set_ylabel('R2 Middle')
axes[2, 0].set_ylabel('R2 Low')
axes[2, 0].set_xlabel("Month")
axes[2, 1].set_xlabel("Month")
"""
plt.setp(axes[0, 0].get_xticklabels(), visible=False)
plt.setp(axes[1, 0].get_xticklabels(), visible=False)
plt.setp(axes[0, 1].get_xticklabels(), visible=False)
plt.setp(axes[1, 1].get_xticklabels(), visible=False)
plt.setp(axes[0, 1].get_yticklabels(), visible=False)
plt.setp(axes[1, 1].get_yticklabels(), visible=False)
plt.setp(axes[2, 1].get_yticklabels(), visible=False)
"""
plt.tight_layout()
plt.savefig(save_name, dpi=900)
plt.close()
def plot_param_1g_through_years(data_1g_dic, save_name):
fig, axes = plt.subplots(3, 1)
dates1 = pd.date_range("2003", "2010", freq='MS').append(
pd.date_range("2013", "2017", freq='MS'))
dates = dates1[:-1]
data_A = pd.DataFrame([])
data_theta = pd.DataFrame([])
data_e2 = pd.DataFrame([])
for y in y_list:
data_A = pd.concat([data_A, data_1g_dic[y]["1g_A"]])
data_theta = pd.concat([data_theta, data_1g_dic[y]["1g_theta"]])
data_e2 = pd.concat([data_e2, data_1g_dic[y]["1g_e2"]])
axes[0].plot(dates, data_A['mean'], '-', color="k")
axes[0].fill_between(dates,
data_A['mean'] + 2 * np.sqrt(data_A['std']),
data_A['mean'] - 2 * np.sqrt(data_A['std']),
facecolor='green',
alpha=0.3,
interpolate=True)
axes[0].set_ylim([0, 0.025])
axes[0].set_ylabel('A')
axes[0].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
axes[1].plot(dates, data_theta['mean'], '-', color="k")
axes[1].fill_between(
dates,
data_theta['mean'] + 2 * np.sqrt(data_theta['std']),
data_theta['mean'] - 2 * np.sqrt(data_theta['std']),
facecolor='green',
alpha=0.3,
interpolate=True)
axes[1].set_ylim([-180, 180])
axes[1].set_ylabel('theta')
axes[1].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
axes[2].plot(dates, data_e2['mean'], '-', color="k")
axes[2].fill_between(dates,
data_e2['mean'] + 2 * np.sqrt(data_e2['std']),
data_e2['mean'] - 2 * np.sqrt(data_e2['std']),
facecolor='green',
alpha=0.3,
interpolate=True)
#axes[2].set_ylim([0, 0.025])
axes[2].set_ylabel('e2')
axes[2].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
plt.tight_layout()
plt.savefig(save_name, dpi=900)
plt.close()
def plot_param_2g_through_years(data_2g_dic, save_name):
fig, axes = plt.subplots(3, 2)
dates1 = pd.date_range("2003", "2010", freq='MS').append(
pd.date_range("2013", "2017", freq='MS'))
dates = dates1[:-1]
data_A_np = pd.DataFrame([])
data_A_coastal = pd.DataFrame([])
data_theta_np = pd.DataFrame([])
data_theta_coastal = pd.DataFrame([])
data_e2_np = pd.DataFrame([])
data_e2_coastal = pd.DataFrame([])
for y in y_list:
data_A_np = pd.concat([data_A_np, data_2g_dic[y]["2g_A_polar"]])
data_A_coastal = pd.concat(
[data_A_coastal, data_2g_dic[y]["2g_A_coastal"]])
data_theta_np = pd.concat(
[data_theta_np, data_2g_dic[y]["2g_theta_polar"]])
data_theta_coastal = pd.concat(
[data_theta_coastal, data_2g_dic[y]["2g_theta_coastal"]])
data_e2_np = pd.concat([data_e2_np, data_2g_dic[y]["2g_e2_polar"]])
data_e2_coastal = pd.concat(
[data_e2_coastal, data_2g_dic[y]["2g_e2_coastal"]])
axes[0, 0].plot(dates, data_A_np['mean'], '-', color="k")
axes[0,
0].fill_between(dates,
data_A_np['mean'] + 2 * np.sqrt(data_A_np['std']),
data_A_np['mean'] - 2 * np.sqrt(data_A_np['std']),
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
axes[0, 0].set_ylim([0, 0.025])
axes[0, 0].set_ylabel('A')
axes[0, 0].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
axes[0, 1].plot(dates, data_A_coastal['mean'], '-', color="k")
axes[0, 1].fill_between(
dates,
data_A_coastal['mean'] + 2 * np.sqrt(data_A_coastal['std']),
data_A_coastal['mean'] - 2 * np.sqrt(data_A_coastal['std']),
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
axes[0, 1].set_ylim([0, 0.025])
axes[0, 1].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
axes[1, 0].plot(dates, data_theta_np['mean'], '-', color="k")
axes[1, 0].fill_between(
dates,
data_theta_np['mean'] + 2 * np.sqrt(data_theta_np['std']),
data_theta_np['mean'] - 2 * np.sqrt(data_theta_np['std']),
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
axes[1, 0].set_ylim([-180, 180])
axes[1, 0].set_ylabel('theta')
axes[1, 0].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
axes[1, 1].plot(dates, data_theta_coastal['mean'], '-', color="k")
axes[1, 1].fill_between(dates,
data_theta_coastal['mean'] +
2 * np.sqrt(data_theta_coastal['std']),
data_theta_coastal['mean'] -
2 * np.sqrt(data_theta_coastal['std']),
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
axes[1, 1].set_ylim([-180, 180])
axes[1, 1].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
axes[2, 0].plot(dates, data_e2_np['mean'], '-', color="k")
axes[2, 0].fill_between(
dates,
data_e2_np['mean'] + 2 * np.sqrt(data_e2_np['std']),
data_e2_np['mean'] - 2 * np.sqrt(data_e2_np['std']),
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
#axes[2, 0].set_ylim([0, 0.025])
axes[2, 0].set_ylabel('e2')
axes[2, 0].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
axes[2, 1].plot(dates, data_e2_coastal['mean'], '-', color="k")
axes[2, 1].fill_between(
dates,
data_e2_coastal['mean'] + 2 * np.sqrt(data_e2_coastal['std']),
data_e2_coastal['mean'] - 2 * np.sqrt(data_e2_coastal['std']),
facecolor='lightskyblue',
alpha=0.3,
interpolate=True)
#axes[2, 1].set_ylim([0, 0.025])
axes[2, 1].xaxis.set_major_formatter(mdates.DateFormatter('%y%m'))
#axes[2, 0].set_xlabel("Year")
#axes[2, 1].set_xlabel("Year")
plt.tight_layout()
plt.savefig(save_name, dpi=900)
plt.close()
y_list = [
"03", "04", "05", "06", "07", "08", "09", "10", "13", "14", "15", "16"
]
month_list = [
"01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"
]
data_1g_dic = {}
data_2g_dic = {}
data_3g_dic = {}
for y in y_list:
data_m = pd.DataFrame([])
for m in month_list:
yymm = "20" + y + m
hermert_file_name = "../data/csv_Helmert_30/Helmert_30_" + yymm + ".csv"
data = calc_data.get_1month_hermert_data(hermert_file_name)
data = pd.concat([latlon_ex["Name"], data], axis=1)
#data = data.drop(["Lat", "Lon", "Label", "idx1", "idx2"], axis=1)
rank_np = np.zeros(145**2)
rank_np[data[data.Name == "north_polar"].index] = 1
data["rank_np"] = rank_np
rank_R2 = np.ones(145**2)
rank_R2[data[data.R2 <= (1 / 3)**2].index] = 0
rank_R2[data[data.R2 > (2 / 3)**2].index] = 2
data["rank_R2"] = rank_R2
data = data.dropna()
#https://code.i-harness.com/ja/q/1c29878
print(data.isnull().sum().sum())
data["yymm"] = [pd.to_datetime(yymm, format="%Y%m")] * len(data)
data_m = pd.concat([data_m, data])
#月ごとに全てのエリアの平均などを取得
data_m_1g = data_m.groupby("yymm")[[
"A", "theta", "epsilon2"
]].describe().sort_index(level='yymm')
#月ごとにrank_npで分類したものを取得
data_m_2g = data_m.groupby(["rank_np", "yymm"
])[["A", "theta", "epsilon2"
]].describe().sort_index(level='yymm')
#月ごとにrank_npとrank_R2で分類したものを取得
data_m_3g = data_m.groupby(["rank_np", "rank_R2", "yymm"
])[["A", "theta", "epsilon2"
]].describe().sort_index(level='yymm')
if m_plot == True:
#1gのプロット
save_name_1g = dirs_1g + "1g_" + y + ".png"
plot_param_1g(data_m_1g, save_name_1g)
#2gのプロット
save_name_2g = dirs_2g + "2g_" + y + ".png"
plot_param_2g(data_m_2g, save_name_2g)
#3gのプロット
plot_param_list = ["A", "theta", "epsilon2"]
for item in plot_param_list:
save_name_3g = dirs_3g + item + "/" + "3g_" + y + ".png"
plot_param_3g(data_m_3g, item, save_name_3g)
"""
sns.tsplot(data=data_m_A, ci="sd")
plt.plot(np.nanmean(data_m_A, axis=0))
data_m_theta = data_m[:,:,1].T
sns.tsplot(data=data_m_theta, ci="sd")
data_m_e2 = data_m[:,:,2].T
sns.tsplot(data=data_m_e2, ci="sd")
"""
tmp_1g = {
"1g_A": data_m_1g["A"].loc[:, ["mean", "std", "50%"]],
"1g_theta": data_m_1g["theta"].loc[:, ["mean", "std", "50%"]],
"1g_e2": data_m_1g["epsilon2"].loc[:, ["mean", "std", "50%"]]
}
data_1g_dic[y] = tmp_1g
tmp_2g = {
"2g_A_polar":
data_m_2g.loc[(1), ("A", ["mean", "std", "50%"])],
"2g_A_coastal":
data_m_2g.loc[(0), ("A", ["mean", "std", "50%"])],
"2g_theta_polar":
data_m_2g.loc[(1), ("theta", ["mean", "std", "50%"])],
"2g_theta_coastal":
data_m_2g.loc[(0), ("theta", ["mean", "std", "50%"])],
"2g_e2_polar":
data_m_2g.loc[(1), ("epsilon2", ["mean", "std", "50%"])],
"2g_e2_coastal":
data_m_2g.loc[(0), ("epsilon2", ["mean", "std", "50%"])]
}
data_2g_dic[y] = tmp_2g
tmp_3g = {
"3g_A_polar":
data_m_3g.loc[(1), ("A", ["mean", "std", "50%"])],
"3g_A_coastal":
data_m_3g.loc[(0), ("A", ["mean", "std", "50%"])],
"3g_theta_polar":
data_m_3g.loc[(1), ("theta", ["mean", "std", "50%"])],
"3g_theta_coastal":
data_m_3g.loc[(0), ("theta", ["mean", "std", "50%"])],
"3g_e2_polar":
data_m_3g.loc[(1), ("epsilon2", ["mean", "std", "50%"])],
"3g_e2_coastal":
data_m_3g.loc[(0), ("epsilon2", ["mean", "std", "50%"])]
}
data_3g_dic[y] = tmp_3g
if y_plot == True:
#1g
save_name_1g_year = dirs_year + "1g.png"
plot_param_1g_through_years(data_1g_dic, save_name_1g_year)
#2g
save_name_2g_year = dirs_year + "2g.png"
plot_param_2g_through_years(data_2g_dic, save_name_2g_year)
return data_1g_dic, data_2g_dic, data_3g_dic