import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("C:\\Users\\eden2\\Desktop\\Thesis\\test4\\final_project\\Raw_data_completed_EXP_2_fix_175_participants.csv") ## Import CSV

df = df.rename(columns={'player.choice_val': 'choice_val'})                             ## Changing column name
df = df.rename(columns={"player.environment_info": "environment_info"})
# df["environment_info"] = df["environment_info"].replace([0, 1], ["Balanced", "Unbalanced"])
df.sort_values(by=["participant.code", "player.current_round"], inplace=True)       ## Sort based on Participants & Rounds

df = df[df.choice_val.notnull()]                                                 ## Filter out rows without input (choice)

demo_df = df[["player.age", "player.gender", "player.connect_id"]]
demo_df.fillna(method="ffill", inplace=True)                                    ## Filling demographic info

df[["player.age", "player.gender", "player.connect_id"]] = demo_df[["player.age", "player.gender", "player.connect_id"]] ## Combine df again

df.fillna(method="bfill", inplace=True)

### Export completed Raw Data
# df.to_csv("Raw_data_completed_fix_658_participants.csv")

### DOES ANYONE COMPLETE THE TASK?
# check_not_50_df = df.groupby("participant.code").count()
# print(check_not_50_df)
# check_not_50_df.to_csv("Who_Complete???###.csv")

### Getting the Data ordered (Up to here)

attention_df = df[df["player.attention_result"] == 1]           ##### ONLY WHO PASSED AC

#### Filtering out all the experiment (POS/NEG) trials (FOR TTEST PURPOSES) >>> Need to fix back the attention_df_1 above to attention_df only

# attention_df = attention_df_1[df["environment_info"] == "Balanced"]
attention_df.to_csv("attention_df_EXP_2_165(175).csv")
###############################################################################################################

# pos_df = attention_df[df["player.condition_info"] == 1]         ##### CON 1
# neg_df = attention_df[df["player.condition_info"] == 2]         ##### CON 2

##### 4 Groups (2X2)
# feedback_pos_df = pos_df[df["player.group_info"] == 1]          # feedback_pos
# no_feedback_pos_df = pos_df[df["player.group_info"] == 2]       # no_feedback_pos
#
# feedback_neg_df = neg_df[df["player.group_info"] == 1]          # feedback_neg
# no_feedback_neg_df = neg_df[df["player.group_info"] == 2]       # no_feedback_neg



## EXPORT
attention_df_demo = attention_df.groupby(["participant.code", "player.gender", "player.submission_code"]).agg({"player.age": "mean"})
# attention_df_gender = attention_df.groupby(["participant.code"]).agg({"player.age": "mean"})

#EXPORT

attention_df_demo.to_csv("ATTENTION_DF_DEMO_EXP_2.csv")

new_attention_df_demo = pd.read_csv("C:\\Users\\eden2\\Desktop\\Thesis\\test4\\final_project\\ATTENTION_DF_DEMO_EXP_2.csv")

gender_df = new_attention_df_demo.groupby(["player.gender"])["player.gender"].count()
code_df = new_attention_df_demo.groupby(["player.submission_code"])["player.submission_code"].count()
mean_age_df = new_attention_df_demo.groupby(["player.gender"]).agg({"player.age": "mean"})
sd_age_df = new_attention_df_demo.groupby(["player.gender"]).agg({"player.age": "std"})
# mean_attention_df_demo = new_attention_df_demo.mean("player.age")

mean_age_df["n"] = gender_df
mean_age_df["std"] = sd_age_df
mean_age_df["submission_code"] = code_df

# gender_df.to_csv("GENDER_DF_DEMO.csv")
mean_age_df.to_csv("DEMOGRAPHICS_INFO_EPX_2_165(175).csv")

print(gender_df,mean_age_df,code_df)

     # present the plot

#
# labels = ["Feedback & Positive", "Feedback & Negative", "No Feedback & Positive", "No Feedback & Negative"]
# # labels = ["Feedback & Positive", "Feedback & Negative"]
# balanced_means = all_df_together_Balanced["Risk rate"]
# unbalanced_means = all_df_together_Unbalanced["Risk rate"]
#
# x = np.arange(len(labels))  # the label locations
# width = 0.35  # the width of the bars
#
# fig, ax = plt.subplots()
# rects1 = ax.bar(x - width/2, balanced_means, width, label="Target")
# rects2 = ax.bar(x + width/2, unbalanced_means, width, label="Context")
#
# # Add some text for labels, title and custom x-axis tick labels, etc.
# ax.set_ylabel('Risk rate')
# ax.set_title('Risk rate by Group and Condition')
# ax.set_xticks(x, labels)
# ax.legend()
#
# ax.bar_label(rects1, padding=3)
# ax.bar_label(rects2, padding=3)
#
# fig.tight_layout()
# plt.ylim(0,1)
# plt.show()