# this code tries to analyze the embeddings of the encoder
# %%
import pandas as pd
import os
from inference import Inference, Embedder_t5_encoder, Embedder_t5_decoder
import numpy as np
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt


checkpoint_directory =  'mapping_t5_complete_desc_unit/checkpoint'

BATCH_SIZE = 512

fold = 1
print(f"Inference for fold {fold}")
# import test data
data_path = f"../data_preprocess/exports/dataset/group_{fold}/test_all.csv"
df = pd.read_csv(data_path, skipinitialspace=True)
df = df[df['MDM']].reset_index(drop=True)

# %%
# get target data
data_path = f"../data_preprocess/exports/dataset/group_{fold}/train_all.csv"
train_df = pd.read_csv(data_path, skipinitialspace=True)
# processing to help with selection later
train_df['thing_property'] = train_df['thing'] + " " + train_df['property']

# assign labels
df['thing_property'] = df['thing'] + " " + df['property']
thing_property = df['thing_property'].to_list()
mdm_list = sorted(list(set(thing_property)))

def generate_labels(df, mdm_list):
    output_list = []
    for _, row in df.iterrows():
        pattern = f"{row['thing_property']}"
        try:
            index = mdm_list.index(pattern)
        except ValueError:
            print("Error: value not found in MDM list")
            index = -1
        output_list.append(index)

    return output_list

df['labels'] = generate_labels(df, mdm_list)

# pattern labels
patterns = df['pattern'].to_list()
mdm_pattern_list = sorted(list(set(patterns)))

def generate_pattern_labels(df, mdm_pattern_list):
    output_list = []
    for _, row in df.iterrows():
        pattern = f"{row['pattern']}"
        try:
            index = mdm_pattern_list.index(pattern)
        except ValueError:
            print("Error: value not found in MDM list")
            index = -1
        output_list.append(index)

    return output_list

df['pattern_labels'] = generate_pattern_labels(df, mdm_pattern_list)

# rank labels by counts
top_10_labels = df['labels'].value_counts()[0:10].index.to_list()

indices = df[df['labels'].isin(top_10_labels)].index.to_list()

input_df = df.iloc[indices].reset_index(drop=True)


# %%
def run(step):
    checkpoint_path = os.path.join(checkpoint_directory, f'checkpoint_{step}')
    embedder = Embedder_t5_encoder(checkpoint_path)
    embedder.prepare_dataloader(input_df, batch_size=BATCH_SIZE, max_length=128)
    embedder.create_embedding()
    embeddings = embedder.embeddings
    return embeddings

# %%
embeddings = (run(step=1200))
# Reducing dimensions with t-SNE
tsne = TSNE(n_components=2, random_state=0, perplexity=5)
embeddings_2d = tsne.fit_transform(embeddings)

# t-sne plot with complete labels
labels = input_df['labels']

# Create a color map from labels to colors
unique_labels = np.unique(labels)
colors = plt.cm.jet(np.linspace(0, 1, len(unique_labels)))
label_to_color = dict(zip(unique_labels, colors))

# Plotting
plt.figure(figsize=(8, 6))
for label in unique_labels:
    idx = (labels == label)
    plt.scatter(embeddings_2d[idx, 0], embeddings_2d[idx, 1], color=label_to_color[label], label=label, alpha=0.7)

plt.title('2D t-SNE Visualization of Embeddings of fine-grained labels')
plt.xlabel('Component 1')
plt.ylabel('Component 2')
plt.legend(title='Group')
plt.show()

# %%
# t-sne plot with pattern labels
labels = input_df['pattern_labels']

# Create a color map from labels to colors
unique_labels = np.unique(labels)
colors = plt.cm.jet(np.linspace(0, 1, len(unique_labels)))
label_to_color = dict(zip(unique_labels, colors))

# Plotting
plt.figure(figsize=(8, 6))
for label in unique_labels:
    idx = (labels == label)
    plt.scatter(embeddings_2d[idx, 0], embeddings_2d[idx, 1], color=label_to_color[label], label=label, alpha=0.7)

plt.title('2D t-SNE Visualization of Embeddings of coarse-grained labels')
plt.xlabel('Component 1')
plt.ylabel('Component 2')
plt.legend(title='Group')
plt.show()

##############################################
# %%
# demonstrate decoding to correct output
step = 1200
checkpoint_path = os.path.join(checkpoint_directory, f'checkpoint_{step}')
infer = Inference(checkpoint_path)
infer.prepare_dataloader(input_df, batch_size=BATCH_SIZE, max_length=128)
thing_prediction_list, property_prediction_list = infer.generate()

# add labels too
# thing_actual_list, property_actual_list = decode_preds(pred_labels)
# Convert the list to a Pandas DataFrame
df_out = pd.DataFrame({
    'p_thing': thing_prediction_list, 
    'p_property': property_prediction_list
})
# df_out['p_thing_correct'] = df_out['p_thing'] == df_out['thing']
# df_out['p_property_correct'] = df_out['p_property'] == df_out['property']
input_df = pd.concat([input_df, df_out], axis=1)

condition_correct_thing = input_df['p_thing'] == input_df['thing']
condition_correct_property = input_df['p_property'] == input_df['property']
prediction_mdm_correct = sum(condition_correct_thing & condition_correct_property)
pred_correct_proportion = prediction_mdm_correct/len(input_df)
print(pred_correct_proportion)

# %%
input_df[['thing', 'p_thing', 'property', 'p_property']]


# %%
# def run(step):
#     checkpoint_path = os.path.join(checkpoint_directory, f'checkpoint_{step}')
#     embedder = Embedder_t5_decoder(checkpoint_path)
#     embedder.prepare_dataloader(input_df, batch_size=BATCH_SIZE, max_length=128)
#     embedder.create_embedding()
#     embeddings = embedder.embeddings
#     return embeddings
# 
# # %%
# embeddings = (run(step=1200))
# # Reducing dimensions with t-SNE
# tsne = TSNE(n_components=2, random_state=0, perplexity=5)
# embeddings_2d = tsne.fit_transform(embeddings)
# 
# # t-sne plot with complete labels
# labels = input_df['labels']
# 
# # Create a color map from labels to colors
# unique_labels = np.unique(labels)
# colors = plt.cm.jet(np.linspace(0, 1, len(unique_labels)))
# label_to_color = dict(zip(unique_labels, colors))
# 
# # Plotting
# plt.figure(figsize=(8, 6))
# for label in unique_labels:
#     idx = (labels == label)
#     plt.scatter(embeddings_2d[idx, 0], embeddings_2d[idx, 1], color=label_to_color[label], label=label, alpha=0.7)
# 
# plt.title('2D t-SNE Visualization of Embeddings of fine-grained labels')
# plt.xlabel('Component 1')
# plt.ylabel('Component 2')
# plt.legend(title='Group')
# plt.show()
# 
# # %%
# # t-sne plot with pattern labels
# labels = input_df['pattern_labels']
# 
# # Create a color map from labels to colors
# unique_labels = np.unique(labels)
# colors = plt.cm.jet(np.linspace(0, 1, len(unique_labels)))
# label_to_color = dict(zip(unique_labels, colors))
# 
# # Plotting
# plt.figure(figsize=(8, 6))
# for label in unique_labels:
#     idx = (labels == label)
#     plt.scatter(embeddings_2d[idx, 0], embeddings_2d[idx, 1], color=label_to_color[label], label=label, alpha=0.7)
# 
# plt.title('2D t-SNE Visualization of Embeddings of coarse-grained labels')
# plt.xlabel('Component 1')
# plt.ylabel('Component 2')
# plt.legend(title='Group')
# plt.show()


# %%