Create data_storytelling.py

data_storytelling.py

@@ -0,0 +1,107 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from wordcloud import WordCloud
+
+class DataStoryteller:
+    def __init__(self):
+        pass
+
+    def generate_story(self, data):
+        story = "Data Story:\n\n"
+        
+        # Basic statistics
+        story += self._generate_basic_stats(data)
+        
+        # Correlation analysis
+        story += self._generate_correlation_analysis(data)
+        
+        # Trend analysis
+        story += self._generate_trend_analysis(data)
+        
+        # Distribution analysis
+        story += self._generate_distribution_analysis(data)
+        
+        return story
+
+    def _generate_basic_stats(self, data):
+        stats = data.describe()
+        text = "Basic Statistics:\n"
+        for column in stats.columns:
+            text += f"\n{column}:\n"
+            text += f"  Mean: {stats[column]['mean']:.2f}\n"
+            text += f"  Median: {data[column].median():.2f}\n"
+            text += f"  Min: {stats[column]['min']:.2f}\n"
+            text += f"  Max: {stats[column]['max']:.2f}\n"
+        return text
+
+    def _generate_correlation_analysis(self, data):
+        numeric_data = data.select_dtypes(include=[np.number])
+        corr_matrix = numeric_data.corr()
+        
+        text = "\nCorrelation Analysis:\n"
+        for i in range(len(corr_matrix.columns)):
+            for j in range(i+1, len(corr_matrix.columns)):
+                col1, col2 = corr_matrix.columns[i], corr_matrix.columns[j]
+                corr = corr_matrix.loc[col1, col2]
+                if abs(corr) > 0.5:
+                    text += f"  Strong correlation between {col1} and {col2}: {corr:.2f}\n"
+        return text
+
+    def _generate_trend_analysis(self, data):
+        text = "\nTrend Analysis:\n"
+        for column in data.select_dtypes(include=[np.number]).columns:
+            trend = np.polyfit(range(len(data)), data[column], 1)[0]
+            if trend > 0:
+                text += f"  {column} shows an increasing trend.\n"
+            elif trend < 0:
+                text += f"  {column} shows a decreasing trend.\n"
+            else:
+                text += f"  {column} shows no significant trend.\n"
+        return text
+
+    def _generate_distribution_analysis(self, data):
+        text = "\nDistribution Analysis:\n"
+        for column in data.select_dtypes(include=[np.number]).columns:
+            skewness = data[column].skew()
+            if abs(skewness) < 0.5:
+                text += f"  {column} is approximately symmetrically distributed.\n"
+            elif skewness > 0:
+                text += f"  {column} is right-skewed.\n"
+            else:
+                text += f"  {column} is left-skewed.\n"
+        return text
+
+    def generate_word_cloud(self, data, text_column):
+        text = " ".join(data[text_column].astype(str))
+        wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
+        
+        plt.figure(figsize=(10, 5))
+        plt.imshow(wordcloud, interpolation='bilinear')
+        plt.axis('off')
+        plt.title('Word Cloud')
+        
+        return plt
+
+    def generate_summary_dashboard(self, data):
+        fig, axs = plt.subplots(2, 2, figsize=(20, 15))
+        
+        # Histogram
+        sns.histplot(data=data, x=data.select_dtypes(include=[np.number]).columns[0], ax=axs[0, 0])
+        axs[0, 0].set_title('Distribution of ' + data.select_dtypes(include=[np.number]).columns[0])
+        
+        # Scatter plot
+        sns.scatterplot(data=data, x=data.select_dtypes(include=[np.number]).columns[0], 
+                        y=data.select_dtypes(include=[np.number]).columns[1], ax=axs[0, 1])
+        axs[0, 1].set_title('Scatter Plot')
+        
+        # Box plot
+        sns.boxplot(data=data, y=data.select_dtypes(include=[np.number]).columns[0], ax=axs[1, 0])
+        axs[1, 0].set_title('Box Plot')
+        
+        # Correlation heatmap
+        sns.heatmap(data.select_dtypes(include=[np.number]).corr(), annot=True, cmap='coolwarm', ax=axs[1, 1])
+        axs[1, 1].set_title('Correlation Heatmap')
+        
+        plt.tight_layout()
+        return fig