#!/usr/bin/env python
# coding: utf-8

# In[1]:


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.neural_network import MLPRegressor
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
from sklearn.model_selection import train_test_split


# In[2]:


df = pd.read_csv("Data.csv")


# In[3]:


df.info()
df.describe()


# In[4]:


df.isnull().sum()


# In[5]:


# Drop rows where variables (except MXT, MNT) have missing values
df = df.dropna(subset=["TEM", "SLP", "RIN"])


# In[6]:


df["MXT"].fillna(df["MXT"].mean(), inplace=True)
df["MNT"].fillna(df["MNT"].mean(), inplace=True)


# In[7]:


df.isnull().sum()


# In[9]:


def normalize(series):
    return 0.1 + 0.8 * (series - series.min()) / (series.max() - series.min())

# Target variable (maximum temperature)
y = df["MXT"]

# All other variables used as predictors
X = df.drop(columns=["MXT", "Year", "Month", "Day"])

# Normalize predictors
X_norm = X.apply(normalize)
y_norm = normalize(y)


# In[10]:


seed = 210412

X_train, X_test, y_train, y_test = train_test_split(
    X_norm, y_norm, test_size=0.20, random_state=seed
)


# In[11]:


model = MLPRegressor(hidden_layer_sizes=(20, 20),
                     max_iter=1000,
                     random_state=seed)

model.fit(X_train, y_train)


# In[12]:


y_pred_train = model.predict(X_train)
y_pred_test = model.predict(X_test)
y_pred_all = model.predict(X_norm)


# In[13]:


train_mse = mean_squared_error(y_train, y_pred_train)
train_mae = mean_absolute_error(y_train, y_pred_train)
train_r2 = r2_score(y_train, y_pred_train)


# In[14]:


test_mse = mean_squared_error(y_test, y_pred_test)
test_mae = mean_absolute_error(y_test, y_pred_test)
test_r2 = r2_score(y_test, y_pred_test)


# In[15]:


overall_mse = mean_squared_error(y_norm, y_pred_all)
overall_mae = mean_absolute_error(y_norm, y_pred_all)
overall_r2 = r2_score(y_norm, y_pred_all)


# In[16]:


print("Training Metrics:")
print(train_mse, train_mae, train_r2)

print("\nTesting Metrics:")
print(test_mse, test_mae, test_r2)

print("\nOverall Metrics:")
print(overall_mse, overall_mae, overall_r2)


# In[ ]:





# In[18]:


plt.figure(figsize=(6, 4))
plt.scatter(y_train, y_pred_train, color="red", label="Training", s=20)
plt.scatter(y_test, y_pred_test, color="skyblue", label="Test", s=20)
plt.xlabel("Actual")
plt.ylabel("Predicted")
plt.title("Actual vs Predicted")
plt.legend()
plt.show()


# In[1]:


import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPRegressor
from sklearn.metrics import r2_score, mean_squared_error
import matplotlib.pyplot as plt
df = pd.read_csv("Data.csv")


df.head()


# In[2]:



df = df.dropna()
df.columns


# In[3]:



def custom_scale(x):
    return 0.1 + 0.8 * ( (x - x.min()) / (x.max() - x.min()) )

scaled_df = df.copy()
for col in df.columns:
    if col not in ["Year", "Month", "Day"]:
        scaled_df[col] = custom_scale(df[col])

scaled_df.head()


# In[4]:



seed = 210412 

X = scaled_df[["TEM","MXT","MNT","HUM","SLP","WIS","SSH","CLD"]]


y = scaled_df["RIN"]
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=seed
)


# In[5]:



model = MLPRegressor(hidden_layer_sizes=(10,10),
                     activation="relu",
                     solver="adam",
                     max_iter=2000,
                     random_state=seed)

model.fit(X_train, y_train)

# Predictions
train_pred = model.predict(X_train)
test_pred  = model.predict(X_test)


# In[6]:



print("TRAIN R²:", r2_score(y_train, train_pred))
print("TEST  R²:", r2_score(y_test,  test_pred))

print("\nTRAIN RMSE:", np.sqrt(mean_squared_error(y_train, train_pred)))
print("TEST  RMSE:", np.sqrt(mean_squared_error(y_test,  test_pred)))


# In[7]:



plt.figure(figsize=(7,6))
plt.scatter(y_train, train_pred, alpha=0.6)
plt.xlabel("Actual Maximum Rainfall (RIN)")
plt.ylabel("Predicted Maximum Rainfall (RIN)")
plt.title("TRAIN DATA: Actual vs Predicted Maximum Rainfall")
plt.grid(True)
plt.show()


# In[8]:



plt.figure(figsize=(7,6))
plt.scatter(y_test, test_pred, alpha=0.6, color="orange")
plt.xlabel("Actual Maximum Rainfall (RIN)")
plt.ylabel("Predicted Maximum Rainfall (RIN)")
plt.title("TEST DATA: Actual vs Predicted Maximum Rainfall")
plt.grid(True)
plt.show()


# In[9]:



overall_pred = model.predict(X)

plt.figure(figsize=(7,6))
plt.scatter(scaled_df["RIN"], overall_pred, alpha=0.6, color="green")
plt.xlabel("Actual Maximum Rainfall (RIN)")
plt.ylabel("Predicted Maximum Rainfall (RIN)")
plt.title("OVERALL DATA: Actual vs Predicted Maximum Rainfall")
plt.grid(True)
plt.show()