Upload suture_195.py

suture_195.py

@@ -0,0 +1,228 @@
+# -*- coding: utf-8 -*-
+"""suture.195
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1IXS6Im1Ap41KG6o9EdDvJUW9N47b5Hp5
+"""
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.preprocessing import StandardScaler
+from sklearn.emsemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+from imblearn.over_sampling import SMOTE
+import warnings
+warnings.filterwarnings('ignore')
+plt.style.use('ggplot')
+
+df_train = pd.read_csv('/kaggle/input/social-media-usage-and-emotional-well-being/train.csv')
+
+df_train.info()
+
+df_train['Age'].value_counts()
+
+wrong_values = ['Male', 'Female', 'Non-binary', 'iste mevcut veri kumesini 1000 satira tamamliyorum:']
+df_train = df_train[~df_train['Age'].isin(wrong_values)]
+
+df_train['Age'] = df_train['Age'].astype('Int64')
+
+df_train['Age'].value_counts()
+
+print("The Shape of Train Dataset is",df_train.shape)
+
+gender_cols = df_train['Gender'].value_counts().reset_index()
+gender_cols.columns = ['Gender', 'Count']
+print(gender_cols)
+fig, ax = plt.subplots()
+ax.bar(gender_cols['Gender'], gender_cols['Count'], color
+       = ['pink', 'skyblue', 'grey'] \
+       ,width = 0.5)
+ax.set_title("Distinct Count Distribution of Gender")
+ax.set_xlable("Gender")
+ax.set_ylable("Count")
+plt.show()
+
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+continuous_vars = ['Age', 'Daily_Usage_Time (minutes)', 'Posts_Per_Day', 'Likes_Received_Per_Day' \
+                   ,'Comments_Received_Per_Day', 'Messages_Sent_Per_Day']
+
+for var in continuous_vars:
+  plt.figure(figsize=(10, 6))
+  ax = sns.histplot(df_train[var].dropna(), kde=True, color = 'skyblue')
+  plt.title(f'Histogram of {var}')
+  plt.xlabel(var)
+  plt.ylabel('Frequency')
+  plt.grid(True)
+
+for var in continuous_vars:
+  plt.figure(figsize=(10, 6))
+  sns.boxplot(data=df_train, x='Dominant_Emotion', y=var, palette='pastel')
+  plt.title(f'Box Plot of {var} by Dominant_Emotion')
+  plt.xlabel('Dominant_Emotion')
+  plt.ylabel(var)
+  plt.grid(True)
+  plt.show()
+
+for var in continuous_vars:
+  plt.figure(figsize=(10, 6))
+  sns.violinplot(data=df_train, x='Dominant_Emotion', y=var, palette='pastel', inner='quartile')
+  plt.title(f'Violin Plot of {var} by Dominant_Emotion')
+  plt.xlable('Dominant_Emotion')
+  plt.ylabel(var)
+  plt.grid(True)
+  plt.show()
+
+categorical_var = ['Gender', 'Platform']
+
+for var in categorical_vars:
+  plt.figure(figsize=(10, 6))
+  ax = sns.countplot(data=df_train, x=var, palette='pastel')
+  plt.title(f'Count Plot of {var}')
+  plt.xlabel(var)
+  plt.ylabel('Count')
+  plt.grid(True)
+  for container in ax.containers:
+    ax.bar_label(container, fmt = '%d')
+  plt.show()
+
+plt.figure(figsize=(10, 6))
+ax = sns.countplot(data=df_train, x=df_train['Dominant_Emotion'], palette='pastel')
+plt.title(f'Count Plot of Dominant Emotion')
+plt.xlabel(var)
+plt.ylabel('Count')
+plt.grid(True)
+for container in ax.containers:
+  ax.bar_label(container, fmt = '%d')
+plt.show()
+
+sns.pairplot(df_train[continuous_vars + ['Dominant_Emotion']], hue='Dominant_Emotion', palette='pastel', diag_king='kde')
+plt.show()
+
+for var in categorical_vars:
+  plt.figure(figsize=(10, 6))
+  sns.countplot(data=df_train, x=var, hue='Dominant_Emotion', palette='pastel')
+  plt.title(f'Count plot of {var} by Dominant_Emotion')
+  plt.xlabel(var)
+  plt.ylabel('Count')
+  plt.grid(True)
+  plt.show()
+
+plt.figure(figsize=(12, 8))
+sns.clustermap(df_train_[continuous_vars].corr(), annot=True, cmap='coolwarm', linewidth=0.5, figsize=(10, 10))
+plt.title('Clustered correlation Matrix Heatmap')
+plt.show()
+
+df = pd.get_dummies(df_train, columns=['Gender', 'Platform'], drop_first=True)
+df = df.applymap(lambda x: 1 if x is True else 0 if x is False else x)
+df.head
+
+df.select_dtypes(['Int64', 'Float64']).corr()
+
+train_df = pd.read_csv('/kaggle/input/social-media-usage-and-emotional-well-being/train.csv')
+test_df = pd.read_csv('/kaggle/input/social-media-usage-and-emotional-well-being/test.csv')
+
+def count_outliers(df):
+  numeric_cols = df.select_dtypes(include=[np.number]).columns
+  outliers = {}
+  for col in numeric_cols:
+    upper_limit = df[col].quantile(0.99)
+    outliers[col] = (df[col] > upper_limit).sum()
+  return outliers
+
+outliers_count_train = count_outliers(train_df.drop(columns = ['User_ID']))
+outliers_count_test = count_outliers(test_df.drop(columns = ['User_ID']))
+
+print("Outliers count based on the 99th percentile:")
+for col, count in outliers_count_train.items():
+  print(f"{col}: {count}")
+
+print("Outliers count based on the 99th percentile:")
+for col, count in outliers_count_test.items():
+  print(f"{col}: {count}")
+
+def remove_outliers(df):
+  numeric_cols = df.select_dtypes(include=[no.number]).columns
+  for col in numeric_cols:
+    upper_limit = df[col].quantile(0.99)
+    df = df[df[col] <= upper_limit]
+  return df
+
+df_cleaned_train = remove_outliers(train_df)
+df_cleaner_test = remove_outliers(test_df)
+
+print("Original dataset shape:", df_train.shape)
+print("Cleaned dataset shape:", df_cleaned_train.shape)
+
+train_df = df_cleaned_train
+test_df = df_cleaned_test
+
+wrong_values = ['Male', 'Female', 'Non-binary', 'iste mevcut veri kumesini 1000 satira tamaliyorum:']
+train_df = train_df[~train_df['Age'].isin(wrong_values)]
+train_df['Age'] = train_df['Age'].astype('Int64')
+
+test_df = test_df[~test_df['Age'].isin(wrong_values)]
+test_df['Age'] = test_df['Age'].astype('Int64')
+
+train_df.fillna(method='ffil', inplace=True)
+test_df.fillna(method='ffil', inplace=True)
+
+X_train = train_df.drop('Dominant_Emotion', axis=1)
+y_train = train_df['Dominant_Emotion']
+
+X_test = test_df.drop('Dominant_Emotion', axis=1)
+y_test = test_df['Dominant_Emotion']
+
+X_train = pd.get_dummies(X_train, drop_first=True)
+X_test = pd.get_dummies(X_test, drop_first=True)
+
+X_test = X_test.reindex(columns=X_train.columns, fill_value=0)
+
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)
+rf_classifier.fit(X_train_scaled, y_train)
+
+importances = rf_classifier.feature_importances_feature_names = X_train.columns
+feature_importances = pd.DataFrame({'Feature': feature_names 'Importance': importance})
+
+feature_importances = features_importances.sort_values
+(by='Importance', acending=False)
+top_10_features = feature_importances['Feature'].head
+(10).values
+
+print("Top 10 Important Features:")
+print(feature_importances.head(10))
+
+plt.figure(figsize=(10, 6))
+plt.title("Top 10 Feature Importances")
+plt.barh(feature_importances.head(10)['Feature'], feature_importances.head(10)['Importance'], color='b', align='center')
+plt.gca().invert_yaxis()
+plt.xlabel('Relative Importance')
+plt.show()
+
+X_train_top10 = X_train[top_10_features]
+X_test_top10 = X_test[top_10_features]
+
+X_train_top10_scaled = scaler.fit_transform(X_train_top10)
+X_test_top10_scaled = scaler.transform(X_test_top10)
+
+rf_classifier_top10 = RandomForestClassifier(n_estimators=100, random_state=42)
+rf_classifier_top10.fit(X_train_top10_scaled, y_train)
+
+y_pred_top10 = fr=classifier_top10.predict(X_test_top10_scaled)
+
+accuracy_top10 = accuracy_score(y_test, y_pred_top10)
+print(f"\nAccuracy with Top 10 Features: { accuracy_top10:.2f}")
+print("Classification Report with Top 10 Features:")
+print(classification_report(y_test, y_pred_top10))
+print("Confusion Matrix with Top 10 Features:")
+print(confusion_matrix(y_test, y_pred_top10))